{"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/get-embedding-layer","entry":"get_embedding_layer","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":12,"n_papers_ran":1,"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":8,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":12,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":7},"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":"2603.03081","paper":"/paper/arxiv-2603-03081","title":"TAO-Attack: Toward Advanced Optimization-Based Jailbreak Attacks for Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"ZevineXu/TAO-Attack","path":"llm_attacks/base/attack_manager.py","file_url":"https://github.com/ZevineXu/TAO-Attack/blob/HEAD/llm_attacks/base/attack_manager.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0bf2136a7171ae80","mcp_get_code":{"code_sha256":"0bf2136a7171ae80"}},{"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/base/attack_manager.py","file_url":"https://github.com/sail-sg/I-FSJ/blob/HEAD/llm_attacks/base/attack_manager.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0bf2136a7171ae80","mcp_get_code":{"code_sha256":"0bf2136a7171ae80"}},{"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/base/attack_manager.py","file_url":"https://github.com/jiaxiaojunqaq/i-gcg/blob/HEAD/llm_attacks/base/attack_manager.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0bf2136a7171ae80","mcp_get_code":{"code_sha256":"0bf2136a7171ae80"}},{"arxiv_id":"2405.18780","paper":"/paper/quantitative-certification-of-bias-in-large","title":"Quantitative Certification of Bias in Large Language Models","date":"2024-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uiuc-focal-lab/LLMCert-B","path":"utils.py","file_url":"https://github.com/uiuc-focal-lab/LLMCert-B/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"code_sha256_prefix":"e25b264898ca821a","mcp_get_code":{"code_sha256":"e25b264898ca821a"}},{"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/base/attack_manager.py","file_url":"https://github.com/llm-attacks/llm-attacks/blob/HEAD/llm_attacks/base/attack_manager.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0bf2136a7171ae80","mcp_get_code":{"code_sha256":"0bf2136a7171ae80"}},{"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/base/attack_manager.py","file_url":"https://github.com/zhaoyiran924/probe-sampling/blob/HEAD/llm_attacks/base/attack_manager.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"16d7b655a5002ab4","mcp_get_code":{"code_sha256":"16d7b655a5002ab4"}},{"arxiv_id":"2402.16459","paper":"/paper/defending-llms-against-jailbreaking-attacks","title":"Defending LLMs against Jailbreaking Attacks via Backtranslation","date":"2024-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yihanwang617/llm-jailbreaking-defense-backtranslation","path":"GCG/llm_attacks/base/attack_manager.py","file_url":"https://github.com/yihanwang617/llm-jailbreaking-defense-backtranslation/blob/HEAD/GCG/llm_attacks/base/attack_manager.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":"0bf2136a7171ae80","mcp_get_code":{"code_sha256":"0bf2136a7171ae80"}},{"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/base/attack_manager.py","file_url":"https://github.com/rookiezxy/gbtl/blob/HEAD/llm_attacks/base/attack_manager.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"67d1618137d21e9f","mcp_get_code":{"code_sha256":"67d1618137d21e9f"}},{"arxiv_id":"2402.05467","paper":"/paper/rapid-optimization-for-jailbreaking-llms-via","title":"Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia","date":"2024-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"solidshen/ripple_official","path":"src/utils/attack_manager.py","file_url":"https://github.com/solidshen/ripple_official/blob/HEAD/src/utils/attack_manager.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"858d2c8063614c3a","mcp_get_code":{"code_sha256":"858d2c8063614c3a"}},{"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/base/attack_manager.py","file_url":"https://github.com/RookieZxy/GGI-attack/blob/HEAD/GGI-attack/llm_attacks/base/attack_manager.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"08e65c38a5b1c5a1","mcp_get_code":{"code_sha256":"08e65c38a5b1c5a1"}},{"arxiv_id":"2310.15140","paper":"/paper/autodan-automatic-and-interpretable","title":"AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models","date":"2023-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rotaryhammer/code-autodan","path":"autodan/autodan/attack_manager.py","file_url":"https://github.com/rotaryhammer/code-autodan/blob/HEAD/autodan/autodan/attack_manager.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"84f875c06b5ddef8","mcp_get_code":{"code_sha256":"84f875c06b5ddef8"}},{"arxiv_id":"2008.00623","paper":"/paper/delight-very-deep-and-light-weight","title":"DeLighT: Deep and Light-weight Transformer","date":"2020-08-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sacmehta/delight","path":"fairseq/delight_modules/nn_functions.py","file_url":"https://github.com/sacmehta/delight/blob/HEAD/fairseq/delight_modules/nn_functions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2e619b36f4ddb228","mcp_get_code":{"code_sha256":"2e619b36f4ddb228"}}]}