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/chiayi-hsu/ring-a-bell

공식 코드

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

https://github.com/dapurv5/awesome-red-teaming-llms

공식 코드

Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)

https://github.com/declare-lab/ferret

공식 코드

Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique

https://github.com/declare-lab/red-instruct

공식 코드

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

https://github.com/facebookresearch/advprompter

공식 코드

AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs

https://github.com/facebookresearch/seamless_communication

공식 코드

Seamless: Multilingual Expressive and Streaming Speech Translation

https://github.com/fisht0ucher/trident

공식 코드

TRIDENT: Enhancing Large Language Model Safety with Tri-Dimensional Diversified Red-Teaming Data Synthesis

https://github.com/git-disl/virus

공식 코드

Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation

https://github.com/google-research-datasets/adversarial-nibbler

공식 코드

Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image Generation

https://github.com/google-research/google-research

공식 코드

Gradient-Based Language Model Red Teaming

https://github.com/govtech-responsibleai/rabakbench

공식 코드

RabakBench: Scaling Human Annotations to Construct Localized Multilingual Safety Benchmarks for Low-Resource Languages

https://github.com/guanlinlee/art

공식 코드

ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users

https://github.com/guanzihan/benign-samples-matter

공식 코드

Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety

https://github.com/haneul-yoo/csrt

공식 코드

Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual Understanding

https://github.com/healthylaife/faircdsllm

공식 코드

Bias patterns in the application of LLMs for clinical decision support: A comprehensive study

https://github.com/improbable-ai/curiosity_redteam

공식 코드

Curiosity-driven Red-teaming for Large Language Models

https://github.com/jankowskichristopher/red-teaming-segment-anything-model

공식 코드

Red-Teaming Segment Anything Model

https://github.com/jc-ryan/holistic_automated_red_teaming

공식 코드

Holistic Automated Red Teaming for Large Language Models through Top-Down Test Case Generation and Multi-turn Interaction

https://github.com/jiaxiaojunqaq/i-gcg

공식 코드

Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

https://github.com/joycenerd/p4d

공식 코드

Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts

https://github.com/juliusbroomfield/the-ssg-problem

공식 코드

The Structural Safety Generalization Problem

https://github.com/kalyan-nakka/bitbypass

공식 코드

BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage

https://github.com/kevinyaobytedance/llm_unlearn

공식 코드

Large Language Model Unlearning

https://github.com/knoveleng/rainbowplus

공식 코드

RainbowPlus: Enhancing Adversarial Prompt Generation via Evolutionary Quality-Diversity Search

https://github.com/kotekjedi/capability-based-scaling

공식 코드

Capability-Based Scaling Laws for LLM Red-Teaming

https://github.com/kriti-hippo/red_queen

공식 코드

RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn Jailbreaking

https://github.com/lakeraai/dsec-gandalf

공식 코드

Gandalf the Red: Adaptive Security for LLMs

https://github.com/leondz/garak

공식 코드

garak: A Framework for Security Probing Large Language Models

https://github.com/likenneth/dialogue_action_token

공식 코드

Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner

https://github.com/lilianngweta/aligners

공식 코드

Aligners: Decoupling LLMs and Alignment

https://github.com/lilianngweta/aligners-and-inspectors

공식 코드

Aligners: Decoupling LLMs and Alignment

https://github.com/littlelittlenine/safemcp

공식 코드

We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems

https://github.com/llm-tuning-safety/llms-finetuning-safety

공식 코드

Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

https://github.com/luka-group/contraDialog

공식 코드

Red Teaming Language Models for Processing Contradictory Dialogues

https://github.com/malusamayo/SemSlicer

공식 코드

What Is Wrong with My Model? Identifying Systematic Problems with Semantic Data Slicing

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

공식 코드

RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments

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