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/AIM-Intelligence/SUDO

공식 코드

sudo rm -rf agentic_security

https://github.com/BillChan226/AgentPoison

공식 코드

AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases

https://github.com/Carol-gutianle/MLLMGuard

공식 코드

MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models

https://github.com/ErxinYu/CoSafe-Dataset

공식 코드

CoSafe: Evaluating Large Language Model Safety in Multi-Turn Dialogue Coreference

https://github.com/GFNOrg/red-teaming

공식 코드

Learning diverse attacks on large language models for robust red-teaming and safety tuning

https://github.com/IDEA-XL/ChemSafety

공식 코드

SMILES-Prompting: A Novel Approach to LLM Jailbreak Attacks in Chemical Synthesis

https://github.com/Isaac-theori/PCJailbreak

공식 코드

BiasJailbreak:Analyzing Ethical Biases and Jailbreak Vulnerabilities in Large Language Models

https://github.com/LeapLabTHU/diver-ct

공식 코드

DiveR-CT: Diversity-enhanced Red Teaming Large Language Model Assistants with Relaxing Constraints

https://github.com/Libr-AI/OpenRedTeaming

공식 코드

Against The Achilles' Heel: A Survey on Red Teaming for Generative Models

https://github.com/Madhur-1/SageLLMSafetyEval

공식 코드

$\texttt{SAGE}$: A Generic Framework for LLM Safety Evaluation

https://github.com/Meirtz/BabyBLUE-llm

공식 코드

"Not Aligned" is Not "Malicious": Being Careful about Hallucinations of Large Language Models' Jailbreak

https://github.com/NY1024/BAP-Jailbreak-Vision-Language-Models-via-Bi-Modal-Adversarial-Prompt

공식 코드

Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt

https://github.com/RossNordby/SoftPromptsForEvaluation

공식 코드

Soft Prompts for Evaluation: Measuring Conditional Distance of Capabilities

https://github.com/SaFoLab-WISC/OET

공식 코드

OET: Optimization-based prompt injection Evaluation Toolkit

https://github.com/TrustMLRG/GASP

공식 코드

GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs

https://github.com/Waffle-Liu/DeGCG

공식 코드

Advancing Adversarial Suffix Transfer Learning on Aligned Large Language Models

https://github.com/YangHao97/RedteamAudioLMMs

공식 코드

Audio Is the Achilles' Heel: Red Teaming Audio Large Multimodal Models

https://github.com/aatrox103/sap

공식 코드

Attack Prompt Generation for Red Teaming and Defending Large Language Models

https://github.com/aengusl/latent-adversarial-training

공식 코드

Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs

https://github.com/ag8/sha-transformer

공식 코드

Unelicitable Backdoors in Language Models via Cryptographic Transformer Circuits

https://github.com/ai-secure/udora

공식 코드

UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning

https://github.com/alexmeigz/assert

공식 코드

ASSERT: Automated Safety Scenario Red Teaming for Evaluating the Robustness of Large Language Models

https://github.com/algorithmic-alignment-lab/commonclaim

공식 코드

Explore, Establish, Exploit: Red Teaming Language Models from Scratch

https://github.com/aliasad059/reddebate

공식 코드

RedDebate: Safer Responses through Multi-Agent Red Teaming Debates

https://github.com/allenai/wildteaming

공식 코드

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

https://github.com/anthropics/hh-rlhf

공식 코드

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

https://github.com/anugyas/nluproject

공식 코드

No Offense Taken: Eliciting Offensiveness from Language Models

https://github.com/asacooperstickland/kl-then-steer

공식 코드

Steering Without Side Effects: Improving Post-Deployment Control of Language Models

https://github.com/azure/pyrit

공식 코드

PyRIT: A Framework for Security Risk Identification and Red Teaming in Generative AI System

https://github.com/babelscape/alert

공식 코드

ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming

https://github.com/boychaboy/ricota

공식 코드

RICoTA: Red-teaming of In-the-wild Conversation with Test Attempts

https://github.com/caoyuanpu/backdoorunalign

공식 코드

Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections

https://github.com/casperllm/casper

공식 코드

Causality Analysis for Evaluating the Security of Large Language Models

https://github.com/centerforaisafety/harmbench

공식 코드

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

https://github.com/charlesgong12/rece

공식 코드

Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models

https://github.com/chenxshuo/redteaminggpt4v

공식 코드

Red Teaming GPT-4V: Are GPT-4V Safe Against Uni/Multi-Modal Jailbreak Attacks?

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