{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/spam-detection","name":"Spam detection","slug":"spam-detection","description_markdown":null,"categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":117,"papers_with_code":38,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":2,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/spam-detection-on-context-specific-spam","slug":"spam-detection-on-context-specific-spam","dataset":"Traditional and Context-specific Spam Twitter","dataset_url":"/dataset/context-specific-spam","rows_in_archive":1,"metrics":["Avg F1"],"first_row_in_archive_order":{"model":"BERT","paper_title":"Traditional and context-specific spam detection in low resource settings","paper_url":"/paper/traditional-and-context-specific-spam","paper_date":"2022-06-09","arxiv_id":null,"code_links":[{"title":"GU-DataLab/context-spam","url":"https://github.com/GU-DataLab/context-spam"}],"syntology":null}}],"datasets":[{"url":"/dataset/vispamreviews","name":"ViSpamReviews","full_name":"Vietnamese Spam Reviews Detection","num_papers_in_archive":3},{"url":"/dataset/context-specific-spam","name":"Traditional and Context-specific Spam Twitter","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/context-specific-spam-detection","name":"Context-specific Spam Detection"},{"url":"/task/traditional-spam-detection","name":"Traditional Spam Detection"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":117,"of_with_code":38,"tagged_in_all":117,"counts":{"archive_papers_tagged":117,"with_a_code_link":38,"where_syntology_ran_a_sample":7,"not_listed_spam_title":0,"listed":117,"listed_where_code_ran":7,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":7,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":7,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/gad-nr-graph-anomaly-detection-via","slug":"gad-nr-graph-anomaly-detection-via","title":"GAD-NR: Graph Anomaly Detection via Neighborhood Reconstruction","date":"2023-06-02","arxiv_id":"2306.01951","repositories_listed":2,"syntology":null},{"url":"/paper/grouped-pointwise-convolutions-reduce","slug":"grouped-pointwise-convolutions-reduce","title":"Grouped Pointwise Convolutions Reduce Parameters in Convolutional Neural Networks","date":"2022-06-30","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/deep-convolutional-forest-a-dynamic-deep","slug":"deep-convolutional-forest-a-dynamic-deep","title":"Deep convolutional forest: a dynamic deep ensemble approach for spam detection in text","date":"2021-10-10","arxiv_id":"2110.15718","repositories_listed":2,"syntology":null},{"url":"/paper/weight-poisoning-attacks-on-pre-trained","slug":"weight-poisoning-attacks-on-pre-trained","title":"Weight Poisoning Attacks on Pre-trained Models","date":"2020-04-14","arxiv_id":"2004.06660","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/weight-poisoning-attacks-on-pre-trained#ran","syntology_url":"https://syntology.ai/paper/2004.06660","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.06660"}},"official":{"repos":["neulab/RIPPLe"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/training-robust-tree-ensembles-for-security","slug":"training-robust-tree-ensembles-for-security","title":"Cost-Aware Robust Tree Ensembles for Security Applications","date":"2019-12-03","arxiv_id":"1912.01149","repositories_listed":2,"syntology":null},{"url":"/paper/gans-for-semi-supervised-opinion-spam","slug":"gans-for-semi-supervised-opinion-spam","title":"GANs for Semi-Supervised Opinion Spam Detection","date":"2019-03-19","arxiv_id":"1903.08289","repositories_listed":2,"syntology":null},{"url":"/paper/stronger-data-poisoning-attacks-break-data","slug":"stronger-data-poisoning-attacks-break-data","title":"Stronger Data Poisoning Attacks Break Data Sanitization Defenses","date":"2018-11-02","arxiv_id":"1811.00741","repositories_listed":2,"syntology":null},{"url":"/paper/evading-classifiers-in-discrete-domains-with","slug":"evading-classifiers-in-discrete-domains-with","title":"Evading classifiers in discrete domains with provable optimality guarantees","date":"2018-10-25","arxiv_id":"1810.10939","repositories_listed":2,"syntology":null},{"url":"/paper/black-box-generation-of-adversarial-text","slug":"black-box-generation-of-adversarial-text","title":"Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers","date":"2018-01-13","arxiv_id":"1801.04354","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/black-box-generation-of-adversarial-text#ran","syntology_url":"https://syntology.ai/paper/1801.04354","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.04354"}},"official":{"repos":["QData/deepWordBug"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cyber-security-data-science-machine-learning","slug":"cyber-security-data-science-machine-learning","title":"Cyber Security Data Science: Machine Learning Methods and their Performance on Imbalanced Datasets","date":"2025-05-07","arxiv_id":"2505.04204","repositories_listed":1,"syntology":null},{"url":"/paper/advancing-email-spam-detection-leveraging","slug":"advancing-email-spam-detection-leveraging","title":"Advancing Email Spam Detection: Leveraging Zero-Shot Learning and Large Language Models","date":"2025-05-05","arxiv_id":"2505.02362","repositories_listed":1,"syntology":null},{"url":"/paper/quickcharnet-an-efficient-url-classification","slug":"quickcharnet-an-efficient-url-classification","title":"QuickCharNet: An Efficient URL Classification Framework for Enhanced Search Engine Optimization","date":"2024-10-22","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/online-detection-and-infographic-explanation","slug":"online-detection-and-infographic-explanation","title":"Online detection and infographic explanation of spam reviews with data drift adaptation","date":"2024-06-21","arxiv_id":"2406.15038","repositories_listed":1,"syntology":null},{"url":"/paper/spamdam-towards-privacy-preserving-and","slug":"spamdam-towards-privacy-preserving-and","title":"SpamDam: Towards Privacy-Preserving and Adversary-Resistant SMS Spam Detection","date":"2024-04-15","arxiv_id":"2404.09481","repositories_listed":1,"syntology":null},{"url":"/paper/detecting-value-expressive-text-posts-in","slug":"detecting-value-expressive-text-posts-in","title":"Detecting value-expressive text posts in Russian social media","date":"2023-12-14","arxiv_id":"2312.08968","repositories_listed":1,"syntology":null},{"url":"/paper/text-generation-for-dataset-augmentation-in","slug":"text-generation-for-dataset-augmentation-in","title":"Text generation for dataset augmentation in security classification tasks","date":"2023-10-22","arxiv_id":"2310.14429","repositories_listed":1,"syntology":null},{"url":"/paper/high-performance-computing-applied-to","slug":"high-performance-computing-applied-to","title":"High Performance Computing Applied to Logistic Regression: A CPU and GPU Implementation Comparison","date":"2023-08-19","arxiv_id":"2308.10037","repositories_listed":1,"syntology":null},{"url":"/paper/addressing-the-impact-of-localized-training","slug":"addressing-the-impact-of-localized-training","title":"Addressing the Impact of Localized Training Data in Graph Neural Networks","date":"2023-07-24","arxiv_id":"2307.12689","repositories_listed":1,"syntology":null},{"url":"/paper/alfred-a-system-for-prompted-weak-supervision","slug":"alfred-a-system-for-prompted-weak-supervision","title":"Alfred: A System for Prompted Weak Supervision","date":"2023-05-29","arxiv_id":"2305.18623","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/alfred-a-system-for-prompted-weak-supervision#ran","syntology_url":"https://syntology.ai/paper/2305.18623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18623"}},"official":{"repos":["batsresearch/alfred"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/spam-t5-benchmarking-large-language-models","slug":"spam-t5-benchmarking-large-language-models","title":"Spam-T5: Benchmarking Large Language Models for Few-Shot Email Spam Detection","date":"2023-04-03","arxiv_id":"2304.01238","repositories_listed":1,"syntology":null},{"url":"/paper/modeling-user-behavior-with-interaction","slug":"modeling-user-behavior-with-interaction","title":"Modeling User Behavior With Interaction Networks for Spam Detection","date":"2022-07-21","arxiv_id":"2207.10767","repositories_listed":1,"syntology":null},{"url":"/paper/traditional-and-context-specific-spam","slug":"traditional-and-context-specific-spam","title":"Traditional and context-specific spam detection in low resource settings","date":"2022-06-09","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/tlmote-a-topic-based-language-modelling","slug":"tlmote-a-topic-based-language-modelling","title":"TLMOTE: A Topic-based Language Modelling Approach for Text Oversampling","date":"2022-05-04","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/using-bert-encoding-to-tackle-the-mad-lib","slug":"using-bert-encoding-to-tackle-the-mad-lib","title":"Using BERT Encoding to Tackle the Mad-lib Attack in SMS Spam Detection","date":"2021-07-13","arxiv_id":"2107.06400","repositories_listed":1,"syntology":null},{"url":"/paper/accelerating-large-scale-real-time-gnn","slug":"accelerating-large-scale-real-time-gnn","title":"Accelerating Large Scale Real-Time GNN Inference using Channel Pruning","date":"2021-05-10","arxiv_id":"2105.04528","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/accelerating-large-scale-real-time-gnn#ran","syntology_url":"https://syntology.ai/paper/2105.04528","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.04528"}},"official":{"repos":["tedzhouhk/GCNP"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/grasp-a-library-for-extracting-and-exploring","slug":"grasp-a-library-for-extracting-and-exploring","title":"GrASP: A Library for Extracting and Exploring Human-Interpretable Textual Patterns","date":"2021-04-08","arxiv_id":"2104.03958","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/grasp-a-library-for-extracting-and-exploring#ran","syntology_url":"https://syntology.ai/paper/2104.03958","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.03958"}},"official":{"repos":["plkumjorn/GrASP"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/adversarial-robustness-with-non-uniform","slug":"adversarial-robustness-with-non-uniform","title":"Adversarial Robustness with Non-uniform Perturbations","date":"2021-02-24","arxiv_id":"2102.12002","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adversarial-robustness-with-non-uniform#ran","syntology_url":"https://syntology.ai/paper/2102.12002","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.12002"}},"official":{"repos":["amazon-research/adversarial-robustness-with-nonuniform-perturbations"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/leveraging-gpt-2-for-classifying-spam-reviews","slug":"leveraging-gpt-2-for-classifying-spam-reviews","title":"Leveraging GPT-2 for Classifying Spam Reviews with Limited Labeled Data via Adversarial Training","date":"2020-12-24","arxiv_id":"2012.13400","repositories_listed":1,"syntology":null},{"url":"/paper/fact-or-factitious-contextualized-opinion-1","slug":"fact-or-factitious-contextualized-opinion-1","title":"Fact or Factitious? Contextualized Opinion Spam Detection","date":"2020-10-29","arxiv_id":"2010.15296","repositories_listed":1,"syntology":null},{"url":"/paper/rank-over-class-the-untapped-potential-of","slug":"rank-over-class-the-untapped-potential-of","title":"Rank over Class: The Untapped Potential of Ranking in Natural Language Processing","date":"2020-09-10","arxiv_id":"2009.05160","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rank-over-class-the-untapped-potential-of#ran","syntology_url":"https://syntology.ai/paper/2009.05160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.05160"}},"official":{"repos":["atapour/rank-over-class"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/deepcapture-image-spam-detection-using-deep","slug":"deepcapture-image-spam-detection-using-deep","title":"DeepCapture: Image Spam Detection Using Deep Learning and Data Augmentation","date":"2020-06-16","arxiv_id":"2006.08885","repositories_listed":1,"syntology":null},{"url":"/paper/detect-camouflaged-spam-content-via","slug":"detect-camouflaged-spam-content-via","title":"Detect Camouflaged Spam Content via StoneSkipping: Graph and Text Joint Embedding for Chinese Character Variation Representation","date":"2019-08-30","arxiv_id":"1908.11561","repositories_listed":1,"syntology":null},{"url":"/paper/spotting-collusive-behaviour-of-online-fraud","slug":"spotting-collusive-behaviour-of-online-fraud","title":"Spotting Collective Behaviour of Online Frauds in Customer Reviews","date":"2019-05-31","arxiv_id":"1905.13649","repositories_listed":1,"syntology":null},{"url":"/paper/deepimagespam-deep-learning-based-image-spam","slug":"deepimagespam-deep-learning-based-image-spam","title":"DeepImageSpam: Deep Learning based Image Spam Detection","date":"2018-10-03","arxiv_id":"1810.03977","repositories_listed":1,"syntology":null},{"url":"/paper/non-negative-networks-against-adversarial","slug":"non-negative-networks-against-adversarial","title":"Non-Negative Networks Against Adversarial Attacks","date":"2018-06-15","arxiv_id":"1806.06108","repositories_listed":1,"syntology":null},{"url":"/paper/emfet-e-mail-features-extraction-tool","slug":"emfet-e-mail-features-extraction-tool","title":"EMFET: E-mail Features Extraction Tool","date":"2017-11-22","arxiv_id":"1711.08521","repositories_listed":1,"syntology":null},{"url":"/paper/natural-language-processing-state-of-the-art","slug":"natural-language-processing-state-of-the-art","title":"Natural Language Processing: State of The Art, Current Trends and Challenges","date":"2017-08-17","arxiv_id":"1708.05148","repositories_listed":1,"syntology":null},{"url":"/paper/an-automated-text-categorization-framework","slug":"an-automated-text-categorization-framework","title":"An Automated Text Categorization Framework based on Hyperparameter Optimization","date":"2017-04-06","arxiv_id":"1704.01975","repositories_listed":1,"syntology":null},{"url":null,"slug":"a-comprehensive-analysis-of-adversarial","title":"A Comprehensive Analysis of Adversarial Attacks against Spam Filters","date":"2025-05-04","arxiv_id":"2505.03831","repositories_listed":0,"syntology":null},{"url":null,"slug":"judgment-of-thoughts-courtroom-of-the-binary","title":"Judgment of Thoughts: Courtroom of the Binary Logical Reasoning in Large Language Models","date":"2024-09-25","arxiv_id":"2409.16635","repositories_listed":0,"syntology":null},{"url":null,"slug":"different-victims-same-layout-email-visual","title":"Different Victims, Same Layout: Email Visual Similarity Detection for Enhanced Email Protection","date":"2024-08-29","arxiv_id":"2408.16945","repositories_listed":0,"syntology":null},{"url":null,"slug":"conditional-semi-supervised-data-augmentation","title":"Conditional Semi-Supervised Data Augmentation for Spam Message Detection with Low Resource Data","date":"2024-07-06","arxiv_id":"2407.04990","repositories_listed":0,"syntology":null},{"url":null,"slug":"sms-spam-detection-and-classification-to","title":"SMS Spam Detection and Classification to Combat Abuse in Telephone Networks Using Natural Language Processing","date":"2024-06-04","arxiv_id":"2406.06578","repositories_listed":0,"syntology":null},{"url":null,"slug":"genshin-general-shield-for-natural-language","title":"Genshin: General Shield for Natural Language Processing with Large Language Models","date":"2024-05-29","arxiv_id":"2405.18741","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-robust-autoencoder-ensemble-based-approach","title":"A Robust Autoencoder Ensemble-Based Approach for Anomaly Detection in Text","date":"2024-05-16","arxiv_id":"2405.13031","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainabledetector-exploring-transformer","title":"ExplainableDetector: Exploring Transformer-based Language Modeling Approach for SMS Spam Detection with Explainability Analysis","date":"2024-05-12","arxiv_id":"2405.08026","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-mixture-of-discriminative","title":"Hierarchical mixture of discriminative Generalized Dirichlet classifiers","date":"2024-05-02","arxiv_id":"2405.01778","repositories_listed":0,"syntology":null},{"url":null,"slug":"counteracting-concept-drift-by-learning-with","title":"Counteracting Concept Drift by Learning with Future Malware Predictions","date":"2024-04-14","arxiv_id":"2404.09352","repositories_listed":0,"syntology":null},{"url":null,"slug":"your-finetuned-large-language-model-is","title":"Your Finetuned Large Language Model is Already a Powerful Out-of-distribution Detector","date":"2024-04-07","arxiv_id":"2404.08679","repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-banking-transaction-descriptions","title":"Identifying Banking Transaction Descriptions via Support Vector Machine Short-Text Classification Based on a Specialized Labelled Corpus","date":"2024-03-29","arxiv_id":"2404.08664","repositories_listed":0,"syntology":null},{"url":null,"slug":"introducing-adaptive-continuous-adversarial","title":"Introducing Adaptive Continuous Adversarial Training (ACAT) to Enhance ML Robustness","date":"2024-03-15","arxiv_id":"2403.10461","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-improved-transformer-based-model-for","title":"An Improved Transformer-based Model for Detecting Phishing, Spam, and Ham: A Large Language Model Approach","date":"2023-11-01","arxiv_id":"2311.04913","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-an-effective-email-spam","title":"Building an Effective Email Spam Classification Model with spaCy","date":"2023-03-15","arxiv_id":"2303.08792","repositories_listed":0,"syntology":null},{"url":null,"slug":"sentiment-analysis-and-opinion-mining-on","title":"Sentiment analysis and opinion mining on educational data: A survey","date":"2023-02-08","arxiv_id":"2302.04359","repositories_listed":0,"syntology":null},{"url":null,"slug":"experimenting-with-an-evaluation-framework","title":"Experimenting with an Evaluation Framework for Imbalanced Data Learning (EFIDL)","date":"2023-01-26","arxiv_id":"2301.10888","repositories_listed":0,"syntology":null},{"url":null,"slug":"signed-latent-factors-for-spamming-activity","title":"Signed Latent Factors for Spamming Activity Detection","date":"2022-09-28","arxiv_id":"2209.13814","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-sequence-models-for-text-classification","title":"Deep Sequence Models for Text Classification Tasks","date":"2022-07-18","arxiv_id":"2207.08880","repositories_listed":0,"syntology":null},{"url":null,"slug":"spam-detection-using-bert","title":"Spam Detection Using BERT","date":"2022-06-06","arxiv_id":"2206.02443","repositories_listed":0,"syntology":null},{"url":null,"slug":"opinion-spam-detection-a-new-approach-using","title":"Opinion Spam Detection: A New Approach Using Machine Learning and Network-Based Algorithms","date":"2022-05-26","arxiv_id":"2205.13422","repositories_listed":0,"syntology":null},{"url":null,"slug":"subgroup-fairness-in-graph-based-spam","title":"Are Your Reviewers Being Treated Equally? Discovering Subgroup Structures to Improve Fairness in Spam Detection","date":"2022-04-24","arxiv_id":"2204.11164","repositories_listed":0,"syntology":null},{"url":null,"slug":"email-spam-detection-using-hierarchical","title":"Email Spam Detection Using Hierarchical Attention Hybrid Deep Learning Method","date":"2022-04-15","arxiv_id":"2204.07390","repositories_listed":0,"syntology":null},{"url":null,"slug":"convolutional-neural-networks-for-image-spam","title":"Convolutional Neural Networks for Image Spam Detection","date":"2022-04-02","arxiv_id":"2204.01710","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-you-robert-or-roberta-deceiving-online","title":"Are You Robert or RoBERTa? Deceiving Online Authorship Attribution Models Using Neural Text Generators","date":"2022-03-18","arxiv_id":"2203.09813","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-spam-detection-using-transfer","title":"Universal Spam Detection using Transfer Learning of BERT Model","date":"2022-02-07","arxiv_id":"2202.03480","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-with-labeling-induced-abstentions","title":"Learning with Labeling Induced Abstentions","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-unlearning-learning-polluting-and","title":"An Investigation on Learning, Polluting, and Unlearning the Spam Emails for Lifelong Learning","date":"2021-11-26","arxiv_id":"2111.14609","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-new-semi-supervised-inductive-transfer","title":"A new semi-supervised inductive transfer learning framework: Co-Transfer","date":"2021-08-18","arxiv_id":"2108.07930","repositories_listed":0,"syntology":null},{"url":null,"slug":"sms-spam-detection-through-skip-gram","title":"SMS Spam Detection Through Skip-gram Embeddings and Shallow Networks","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-adversarial-perturbations-and-image","title":"Universal Adversarial Perturbations and Image Spam Classifiers","date":"2021-03-07","arxiv_id":"2103.05469","repositories_listed":0,"syntology":null},{"url":null,"slug":"parallel-algorithms-for-densest-subgraph","title":"Parallel Algorithms for Densest Subgraph Discovery Using Shared Memory Model","date":"2021-02-27","arxiv_id":"2103.00154","repositories_listed":0,"syntology":null},{"url":null,"slug":"additive-feature-hashing","title":"Additive Feature Hashing","date":"2021-02-07","arxiv_id":"2102.03943","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-privacy-preserving-text-classification","title":"Fast Privacy-Preserving Text Classification based on Secure Multiparty Computation","date":"2021-01-18","arxiv_id":"2101.07365","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-practical-test-for-a-planted-community-in","title":"A practical test for a planted community in heterogeneous networks","date":"2021-01-15","arxiv_id":"2101.05928","repositories_listed":0,"syntology":null},{"url":null,"slug":"effective-email-spam-detection-system-using","title":"Effective Email Spam Detection System using Extreme Gradient Boosting","date":"2020-12-27","arxiv_id":"2012.14430","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-opinion-spam-detection-by","title":"Improving Opinion Spam Detection by Cumulative Relative Frequency Distribution","date":"2020-12-27","arxiv_id":"2012.13905","repositories_listed":0,"syntology":null},{"url":null,"slug":"twitter-spam-detection-a-systematic-review","title":"Twitter Spam Detection: A Systematic Review","date":"2020-11-30","arxiv_id":"2011.14754","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-robust-opinion-spam-detection-method","title":"A Robust Opinion Spam Detection Method Against Malicious Attackers in Social Media","date":"2020-08-19","arxiv_id":"2008.08650","repositories_listed":0,"syntology":null},{"url":null,"slug":"camouflaged-chinese-spam-content-detection","title":"Camouflaged Chinese Spam Content Detection with Semi-supervised Generative Active Learning","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"weight-poisoning-attacks-on-pretrained-models","title":"Weight Poisoning Attacks on Pretrained Models","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"biologically-inspired-sleep-algorithm-for-1","title":"Biologically inspired sleep algorithm for increased generalization and adversarial robustness in deep neural networks","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-machine-learning-in-network","title":"Adversarial Machine Learning in Network Intrusion Detection Systems","date":"2020-04-23","arxiv_id":"2004.11898","repositories_listed":0,"syntology":null},{"url":null,"slug":"quarantine-deceiving-yelp-s-users-by","title":"Quarantine Deceiving Yelp's Users by Detecting Unreliable Rating Reviews","date":"2020-04-21","arxiv_id":"2004.09721","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-spoofing-in-content-based-spam","title":"Visual Spoofing in content based spam detection","date":"2020-04-11","arxiv_id":"2004.05265","repositories_listed":0,"syntology":null},{"url":null,"slug":"deepquarantine-for-suspicious-mail","title":"DeepQuarantine for Suspicious Mail","date":"2020-01-13","arxiv_id":"2001.04168","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-review-representations-from-user-and","title":"Learning review representations from user and product level information for spam detection","date":"2019-09-10","arxiv_id":"1909.04455","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-sensitive-malicious-spelling-error","title":"Context-Sensitive Malicious Spelling Error Correction","date":"2019-01-23","arxiv_id":"1901.07688","repositories_listed":0,"syntology":null},{"url":null,"slug":"securing-behavior-based-opinion-spam","title":"Securing Behavior-based Opinion Spam Detection","date":"2018-11-09","arxiv_id":"1811.03739","repositories_listed":0,"syntology":null},{"url":null,"slug":"credit-card-fraud-detection-in-e-commerce-an","title":"Credit Card Fraud Detection in e-Commerce: An Outlier Detection Approach","date":"2018-11-06","arxiv_id":"1811.02196","repositories_listed":0,"syntology":null},{"url":null,"slug":"study-and-observation-of-the-variations-of-1","title":"Study and Observation of the Variations of Accuracies for Handwritten Digits Recognition with Various Hidden Layers and Epochs using Convolutional Neural Network","date":"2018-09-17","arxiv_id":"1809.06187","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-randomness-to-improve-robustness-of","title":"Using Randomness to Improve Robustness of Machine-Learning Models Against Evasion Attacks","date":"2018-08-10","arxiv_id":"1808.03601","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-attribute-enhanced-domain-adaptive-model","title":"An Attribute Enhanced Domain Adaptive Model for Cold-Start Spam Review Detection","date":"2018-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"opinion-spam-recognition-method-for-online","title":"Opinion Spam Recognition Method for Online Reviews using Ontological Features","date":"2018-07-29","arxiv_id":"1807.11024","repositories_listed":0,"syntology":null},{"url":null,"slug":"neyman-pearson-classification-parametrics-and","title":"Neyman-Pearson classification: parametrics and sample size requirement","date":"2018-02-07","arxiv_id":"1802.02557","repositories_listed":0,"syntology":null},{"url":null,"slug":"outlier-detection-by-consistent-data","title":"Outlier Detection by Consistent Data Selection Method","date":"2017-12-12","arxiv_id":"1712.04129","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-accurate-deceptive-opinion-spam","title":"Towards Accurate Deceptive Opinion Spam Detection based on Word Order-preserving CNN","date":"2017-11-25","arxiv_id":"1711.09181","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-systematic-framework-to-discover-pattern","title":"A systematic framework to discover pattern for web spam classification","date":"2017-11-19","arxiv_id":"1711.06955","repositories_listed":0,"syntology":null},{"url":null,"slug":"impact-of-feature-selection-on-micro-text","title":"Impact of Feature Selection on Micro-Text Classification","date":"2017-08-27","arxiv_id":"1708.08123","repositories_listed":0,"syntology":null},{"url":null,"slug":"handling-cold-start-problem-in-review-spam","title":"Handling Cold-Start Problem in Review Spam Detection by Jointly Embedding Texts and Behaviors","date":"2017-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"enwalk-learning-network-features-for-spam","title":"ENWalk: Learning Network Features for Spam Detection in Twitter","date":"2017-04-11","arxiv_id":"1704.03404","repositories_listed":0,"syntology":null},{"url":null,"slug":"netspam-a-network-based-spam-detection","title":"NetSpam: a Network-based Spam Detection Framework for Reviews in Online Social Media","date":"2017-03-10","arxiv_id":"1703.03609","repositories_listed":0,"syntology":null}],"syntology_records":7,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":7,"papers_where_code_ran_first_page":"/task/spam-detection/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/spam-detection/papers/2","json":"/task/spam-detection/papers/2.json","rows":17},{"order":"ran","page":1,"of":1,"url":"/task/spam-detection/papers/ran/1","json":"/task/spam-detection/papers/ran/1.json","rows":7}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"099eb8daeb133e76a0657959247203f9c7cee7cb8c3983f6404947d82fe2ad08","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}