{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/code/sample-control","entry":"sample_control","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":13,"n_papers_ran":0,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":6,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":14,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":6},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2603.00696","paper":"/paper/arxiv-2603-00696","title":"DRIV-EX: Counterfactual Explanations for Driving LLMs","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"Amaia-CARDIEL/DRIV_EX","path":"driv_ex/cf_algorithms/gcg_script.py","file_url":"https://github.com/Amaia-CARDIEL/DRIV_EX/blob/HEAD/driv_ex/cf_algorithms/gcg_script.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"409e9147dd1fe88f","mcp_get_code":{"code_sha256":"409e9147dd1fe88f"}},{"arxiv_id":"2408.14866","paper":"/paper/advancing-adversarial-suffix-transfer","title":"Advancing Adversarial Suffix Transfer Learning on Aligned Large Language Models","date":"2024-08-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Waffle-Liu/DeGCG","path":"baselines/gcg/gcg_utils.py","file_url":"https://github.com/Waffle-Liu/DeGCG/blob/HEAD/baselines/gcg/gcg_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"112080cc850b86b9","mcp_get_code":{"code_sha256":"112080cc850b86b9"}},{"arxiv_id":"2406.10794","paper":"/paper/towards-understanding-jailbreak-attacks-in","title":"Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis","date":"2024-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuplin2333/representation-space-jailbreak","path":"jailbreak_gcg.py","file_url":"https://github.com/yuplin2333/representation-space-jailbreak/blob/HEAD/jailbreak_gcg.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"112080cc850b86b9","mcp_get_code":{"code_sha256":"112080cc850b86b9"}},{"arxiv_id":"2406.01288","paper":"/paper/improved-few-shot-jailbreaking-can-circumvent","title":"Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses","date":"2024-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/I-FSJ","path":"exps/rs.py","file_url":"https://github.com/sail-sg/I-FSJ/blob/HEAD/exps/rs.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1e8c1c46e0ec7dad","mcp_get_code":{"code_sha256":"1e8c1c46e0ec7dad"}},{"arxiv_id":"2406.01288","paper":"/paper/improved-few-shot-jailbreaking-can-circumvent","title":"Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses","date":"2024-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/I-FSJ","path":"llm_attacks/minimal_gcg/opt_utils.py","file_url":"https://github.com/sail-sg/I-FSJ/blob/HEAD/llm_attacks/minimal_gcg/opt_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"94d7ddaf0169dbf1","mcp_get_code":{"code_sha256":"94d7ddaf0169dbf1"}},{"arxiv_id":"2405.21018","paper":"/paper/improved-techniques-for-optimization-based","title":"Improved Techniques for Optimization-Based Jailbreaking on Large Language Models","date":"2024-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiaxiaojunqaq/i-gcg","path":"llm_attacks/minimal_gcg/opt_utils.py","file_url":"https://github.com/jiaxiaojunqaq/i-gcg/blob/HEAD/llm_attacks/minimal_gcg/opt_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"94d7ddaf0169dbf1","mcp_get_code":{"code_sha256":"94d7ddaf0169dbf1"}},{"arxiv_id":"2405.01229","paper":"/paper/boosting-jailbreak-attack-with-momentum","title":"Boosting Jailbreak Attack with Momentum","date":"2024-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"weizeming/momentum-attack-llm","path":"minimal_gcg/opt_utils.py","file_url":"https://github.com/weizeming/momentum-attack-llm/blob/HEAD/minimal_gcg/opt_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"94d7ddaf0169dbf1","mcp_get_code":{"code_sha256":"94d7ddaf0169dbf1"}},{"arxiv_id":"2404.13968","paper":"/paper/protecting-your-llms-with-information","title":"Protecting Your LLMs with Information Bottleneck","date":"2024-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"llm-attacks/llm-attacks","path":"llm_attacks/minimal_gcg/opt_utils.py","file_url":"https://github.com/llm-attacks/llm-attacks/blob/HEAD/llm_attacks/minimal_gcg/opt_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"94d7ddaf0169dbf1","mcp_get_code":{"code_sha256":"94d7ddaf0169dbf1"}},{"arxiv_id":"2403.01446","paper":"/paper/guardt2i-defending-text-to-image-models-from","title":"GuardT2I: Defending Text-to-Image Models from Adversarial Prompts","date":"2024-03-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yangyijune/mma-diffusion","path":"src/textual_attack.py","file_url":"https://github.com/yangyijune/mma-diffusion/blob/HEAD/src/textual_attack.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"64762d38e7f09b9a","mcp_get_code":{"code_sha256":"64762d38e7f09b9a"}},{"arxiv_id":"2403.01251","paper":"/paper/accelerating-greedy-coordinate-gradient-via","title":"Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling","date":"2024-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhaoyiran924/probe-sampling","path":"llm_attacks/minimal_gcg/opt_utils.py","file_url":"https://github.com/zhaoyiran924/probe-sampling/blob/HEAD/llm_attacks/minimal_gcg/opt_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"94d7ddaf0169dbf1","mcp_get_code":{"code_sha256":"94d7ddaf0169dbf1"}},{"arxiv_id":"2402.13459","paper":"/paper/learning-to-poison-large-language-models","title":"Learning to Poison Large Language Models for Downstream Manipulation","date":"2024-02-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rookiezxy/gbtl","path":"llm_attacks/gbtl/opt_utils.py","file_url":"https://github.com/rookiezxy/gbtl/blob/HEAD/llm_attacks/gbtl/opt_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"94d7ddaf0169dbf1","mcp_get_code":{"code_sha256":"94d7ddaf0169dbf1"}},{"arxiv_id":"2402.09154","paper":"/paper/attacking-large-language-models-with","title":"Attacking Large Language Models with Projected Gradient Descent","date":"2024-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sigeisler/reinforce-attacks-llms","path":"baselines/reinforce/gcg_utils.py","file_url":"https://github.com/sigeisler/reinforce-attacks-llms/blob/HEAD/baselines/reinforce/gcg_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2dcbffb713bbdbf4","mcp_get_code":{"code_sha256":"2dcbffb713bbdbf4"}},{"arxiv_id":"2311.17516","paper":"/paper/mma-diffusion-multimodal-attack-on-diffusion","title":"MMA-Diffusion: MultiModal Attack on Diffusion Models","date":"2023-11-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cure-lab/mma-diffusion","path":"src/textual_attack.py","file_url":"https://github.com/cure-lab/mma-diffusion/blob/HEAD/src/textual_attack.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"64762d38e7f09b9a","mcp_get_code":{"code_sha256":"64762d38e7f09b9a"}},{"arxiv_id":"2311.09948","paper":"/paper/hijacking-large-language-models-via","title":"Hijacking Large Language Models via Adversarial In-Context Learning","date":"2023-11-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RookieZxy/GGI-attack","path":"GGI-attack/llm_attacks/ggi/opt_utils.py","file_url":"https://github.com/RookieZxy/GGI-attack/blob/HEAD/GGI-attack/llm_attacks/ggi/opt_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"94d7ddaf0169dbf1","mcp_get_code":{"code_sha256":"94d7ddaf0169dbf1"}}]}