{"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/eta-evaluating-then-aligning-safety-of-vision","title":"ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time","arxiv_id":"2410.06625","date":"2024-10-09","proceeding":null,"authors":["Yi Ding","Bolian Li","Ruqi Zhang"],"abstract":"Vision Language Models (VLMs) have become essential backbones for multimodal intelligence, yet significant safety challenges limit their real-world application. While textual inputs are often effectively safeguarded, adversarial visual inputs can easily bypass VLM defense mechanisms. Existing defense methods are either resource-intensive, requiring substantial data and compute, or fail to simultaneously ensure safety and usefulness in responses. To address these limitations, we propose a novel two-phase inference-time alignment framework, Evaluating Then Aligning (ETA): 1) Evaluating input visual contents and output responses to establish a robust safety awareness in multimodal settings, and 2) Aligning unsafe behaviors at both shallow and deep levels by conditioning the VLMs' generative distribution with an interference prefix and performing sentence-level best-of-N to search the most harmless and helpful generation paths. Extensive experiments show that ETA outperforms baseline methods in terms of harmlessness, helpfulness, and efficiency, reducing the unsafe rate by 87.5% in cross-modality attacks and achieving 96.6% win-ties in GPT-4 helpfulness evaluation. The code is publicly available at https://github.com/DripNowhy/ETA.","url_abs":"https://arxiv.org/abs/2410.06625v1","url_pdf":"https://arxiv.org/pdf/2410.06625v1.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":"eta-evaluating-then-aligning-safety-of-vision","repo_url":"https://github.com/dripnowhy/eta","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.06625","atlas_url":"https://app.syntology.ai/?focus=2410.06625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.06625"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.06625"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.06625"},"call":"get_harvested_code_for_paper(arxiv_id=\"2410.06625\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2410.06625"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2410.06625\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2410.06625"},"call":"get_concepts_for_paper(arxiv_id=\"2410.06625\")"}],"by_repo":[{"repo":"dripnowhy/eta","kind":"official","samples":11,"ran":9,"instrument":4,"unverified":2}],"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","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2410.06625.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2410.06625.svg"},"claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dripnowhy/eta","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"ran_violates":2,"ran_draft_wrong":4,"ran":2,"unverified":2},"n_samples":11,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":2,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"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)"},"by_repo_kind":{"official":{"samples":11,"ran":9,"n_ran_checked":5,"n_instrument":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":11,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":7,"n_ran_without_level_date":2,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-24","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"da2114a8052b6d55","code_sha256_prefix":"da2114a8052b6d55","entry":"calculate_safety_scores","repo":"dripnowhy/eta","repo_kind":"official","path":"eval_usr.py","file_url":"https://github.com/dripnowhy/eta/blob/HEAD/eval_usr.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"data:list/1/dict","fixture_out_type":"list","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dripnowhy/eta when it was checked","mcp_get_code":{"code_sha256":"da2114a8052b6d55"}},{"code_sha256":"8e8f6b744fcf648c","code_sha256_prefix":"8e8f6b744fcf648c","entry":"check_success_attack","repo":"dripnowhy/eta","repo_kind":"official","path":"eval_asr.py","file_url":"https://github.com/dripnowhy/eta/blob/HEAD/eval_asr.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"pred:str/0/str","fixture_out_type":"bool","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dripnowhy/eta when it was checked","mcp_get_code":{"code_sha256":"8e8f6b744fcf648c"}},{"code_sha256":"b3b9db8ec8e0d1d1","code_sha256_prefix":"b3b9db8ec8e0d1d1","entry":"collate_fn","repo":"dripnowhy/eta","repo_kind":"official","path":"llava/eval/model_vqa_loader_eta.py","file_url":"https://github.com/dripnowhy/eta/blob/HEAD/llava/eval/model_vqa_loader_eta.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"batch:list/1/tuple","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/collate-fn","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dripnowhy/eta when it was checked","mcp_get_code":{"code_sha256":"b3b9db8ec8e0d1d1"}},{"code_sha256":"f41cb1a19b154297","code_sha256_prefix":"f41cb1a19b154297","entry":"encode_image","repo":"dripnowhy/eta","repo_kind":"official","path":"helpfulscore_ai.py","file_url":"https://github.com/dripnowhy/eta/blob/HEAD/helpfulscore_ai.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"image_path:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/encode-image","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dripnowhy/eta when it was checked","mcp_get_code":{"code_sha256":"f41cb1a19b154297"}},{"code_sha256":"42a46570620cd9fa","code_sha256_prefix":"42a46570620cd9fa","entry":"get_chunk","repo":"dripnowhy/eta","repo_kind":"official","path":"llava/eval/model_vqa_loader_eta.py","file_url":"https://github.com/dripnowhy/eta/blob/HEAD/llava/eval/model_vqa_loader_eta.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"signature":"lst:list/1/int, n:int/0/int, k:int/0/int","fixture_out_type":"list","retrieve_with":{"tool":"get_code","code_sha256":"42a46570620cd9fa"},"code_page":"/code/get-chunk","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dripnowhy/eta when it was checked","mcp_get_code":{"code_sha256":"42a46570620cd9fa"}},{"code_sha256":"eae64eb562f6b0d1","code_sha256_prefix":"eae64eb562f6b0d1","entry":"gpt4_eval","repo":"dripnowhy/eta","repo_kind":"official","path":"helpfulscore_ai.py","file_url":"https://github.com/dripnowhy/eta/blob/HEAD/helpfulscore_ai.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"str","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dripnowhy/eta when it was checked","mcp_get_code":{"code_sha256":"eae64eb562f6b0d1"}},{"code_sha256":"6d82575864d8ddeb","code_sha256_prefix":"6d82575864d8ddeb","entry":"gpt4_eval","repo":"dripnowhy/eta","repo_kind":"official","path":"helpful_wintie_ai.py","file_url":"https://github.com/dripnowhy/eta/blob/HEAD/helpful_wintie_ai.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"str","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dripnowhy/eta when it was checked","mcp_get_code":{"code_sha256":"6d82575864d8ddeb"}},{"code_sha256":"bae18947b56f2be1","code_sha256_prefix":"bae18947b56f2be1","entry":"is_none","repo":"dripnowhy/eta","repo_kind":"official","path":"llava/eval/model_vqa_mmbench_eta.py","file_url":"https://github.com/dripnowhy/eta/blob/HEAD/llava/eval/model_vqa_mmbench_eta.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"value:NoneType/0/?","fixture_out_type":"bool","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/is-none","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dripnowhy/eta when it was checked","mcp_get_code":{"code_sha256":"bae18947b56f2be1"}},{"code_sha256":"076c252c52cbb161","code_sha256_prefix":"076c252c52cbb161","entry":"split_list","repo":"dripnowhy/eta","repo_kind":"official","path":"llava/eval/model_vqa_loader_eta.py","file_url":"https://github.com/dripnowhy/eta/blob/HEAD/llava/eval/model_vqa_loader_eta.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature":"lst:list/1/int, n:int/0/int","fixture_out_type":"list","retrieve_with":{"tool":"get_code","code_sha256":"076c252c52cbb161"},"code_page":"/code/split-list","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dripnowhy/eta when it was checked","mcp_get_code":{"code_sha256":"076c252c52cbb161"}},{"code_sha256":"85e3fe4d95b795f8","code_sha256_prefix":"85e3fe4d95b795f8","entry":"evaluate_safety","repo":"dripnowhy/eta","repo_kind":"official","path":"eval_usr.py","file_url":"https://github.com/dripnowhy/eta/blob/HEAD/eval_usr.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dripnowhy/eta when it was checked","mcp_get_code":{"code_sha256":"85e3fe4d95b795f8"}},{"code_sha256":"14c54d6727f29560","code_sha256_prefix":"14c54d6727f29560","entry":"get_stopping_criteria","repo":"dripnowhy/eta","repo_kind":"official","path":"modeling_internlm_xcomposer2.py","file_url":"https://github.com/dripnowhy/eta/blob/HEAD/modeling_internlm_xcomposer2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dripnowhy/eta when it was checked","mcp_get_code":{"code_sha256":"14c54d6727f29560"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"dc4c06d6e09924b17aaed982a62fa0940300fd6e6d7cc9da347d1ce157d383fa","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}