https://github.com/IDEA-XL/ChemSafety
공식 코드SMILES-Prompting: A Novel Approach to LLM Jailbreak Attacks in Chemical Synthesis
Papers with Code 아카이브
LLM Jailbreak
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/UNHSAILLab/cognitive-overload-attack
공식 코드https://github.com/allen-piexl/jailbreakzoo
공식 코드https://github.com/beijing-aisi/panda-guard
공식 코드PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
https://github.com/cysecbench/dataset
공식 코드https://github.com/dsbuddy/gap-llm-safety
공식 코드https://github.com/hukkai/adc_llm_attack
공식 코드Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization
https://github.com/microsoft/lmops
공식 코드Automatic Prompt Optimization with "Gradient Descent" and Beam Search
https://github.com/renqibing/actorattack
공식 코드Derail Yourself: Multi-turn LLM Jailbreak Attack through Self-discovered Clues
https://github.com/xndong/sata
공식 코드SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkage
https://github.com/AIM-Intelligence/Automated-Multi-Turn-Jailbreaks
Derail Yourself: Multi-turn LLM Jailbreak Attack through Self-discovered Clues
https://github.com/EddyLuo1232/JailBreakV_28K
https://github.com/batorskq/prl
Automatic Prompt Optimization with "Gradient Descent" and Beam Search
https://github.com/lastmile-ai/aiconfig
Automatic Prompt Optimization with "Gradient Descent" and Beam Search
https://github.com/seasonyao/automatic_prompt_optimization_physician_prompting
Automatic Prompt Optimization with "Gradient Descent" and Beam Search
https://github.com/yongchao98/promst
Automatic Prompt Optimization with "Gradient Descent" and Beam Search
https://github.com/zcrwind/prefer
Automatic Prompt Optimization with "Gradient Descent" and Beam Search
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.