Papers with Code 아카이브

Red Teaming

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

0

평가표

1

보존된 평가 기록

1

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/NVIDIA/garak

garak: A Framework for Security Probing Large Language Models

https://github.com/allenai/safety-eval

WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models

https://github.com/bbartoldson/TBA

Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training

https://github.com/boyiwei/tar-reproduce

Tamper-Resistant Safeguards for Open-Weight LLMs

https://github.com/cassidylaidlaw/hidden-context

Jailbroken: How Does LLM Safety Training Fail?

https://github.com/guangyaodou/SSU_Unlearn

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

https://github.com/hpai-bsc/prompt_engine

Aloe: A Family of Fine-tuned Open Healthcare LLMs

https://github.com/leondiao0427/seas

Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment

https://github.com/lyqcom/red30

Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

https://github.com/matengsysu/himrd-jailbreak

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

https://github.com/nouhadziri/safety-eval-fork

WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models

https://github.com/osu-nlp-group/amplegcg

Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation

https://github.com/ruchikachavhan/concept-prune

Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models?

https://github.com/sheltonliu-n/autodan

AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs

https://github.com/shizhouxing/LLM-Detector-Robustness

Red Teaming Language Model Detectors with Language Models

https://github.com/shreya1313/llm-unlearning

Large Language Model Unlearning

https://github.com/shreyansh26/Red-Teaming-Language-Models-with-Language-Models

Red Teaming Language Models with Language Models

https://github.com/thu-coai/jailbreakdefense_goalpriority

GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.