{"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":"/paper/defending-against-patch-based-backdoor","title":"Defending Against Patch-based Backdoor Attacks on Self-Supervised Learning","arxiv_id":"2304.01482","date":"2023-04-04","proceeding":"CVPR 2023 1","authors":["Ajinkya Tejankar","Maziar Sanjabi","Qifan Wang","Sinong Wang","Hamed Firooz","Hamed Pirsiavash","Liang Tan"],"abstract":"Recently, self-supervised learning (SSL) was shown to be vulnerable to patch-based data poisoning backdoor attacks. It was shown that an adversary can poison a small part of the unlabeled data so that when a victim trains an SSL model on it, the final model will have a backdoor that the adversary can exploit. This work aims to defend self-supervised learning against such attacks. We use a three-step defense pipeline, where we first train a model on the poisoned data. In the second step, our proposed defense algorithm (PatchSearch) uses the trained model to search the training data for poisoned samples and removes them from the training set. In the third step, a final model is trained on the cleaned-up training set. Our results show that PatchSearch is an effective defense. As an example, it improves a model's accuracy on images containing the trigger from 38.2% to 63.7% which is very close to the clean model's accuracy, 64.6%. Moreover, we show that PatchSearch outperforms baselines and state-of-the-art defense approaches including those using additional clean, trusted data. Our code is available at https://github.com/UCDvision/PatchSearch","url_abs":"https://arxiv.org/abs/2304.01482v1","url_pdf":"https://arxiv.org/pdf/2304.01482v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"defending-against-patch-based-backdoor","repo_url":"https://github.com/ucdvision/patchsearch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"defending-against-patch-based-backdoor","repo_url":"https://github.com/jsrdcht/SSL-Backdoor","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-poisoning","task_name":"Data Poisoning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2304.01482","atlas_url":"https://app.syntology.ai/?focus=2304.01482","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2304.01482"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2304.01482\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2304.01482"},"call":"get_concepts_for_paper(arxiv_id=\"2304.01482\")"}],"by_repo":[{"repo":"ucdvision/patchsearch","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"jsrdcht/SSL-Backdoor","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2108.00352"],"harvested_for_calls":[{"arxiv_id":"2108.00352","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2108.00352"},"call":"get_harvested_code_for_paper(arxiv_id=\"2108.00352\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"c548eebd097e24202bef4357edbfa56a6acd0bf90bd87abea52f987fc3c51d28","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}