leondz / autoredteamLinks
autoredteam: code for training models that automatically red team other language models
☆15Updated 2 years ago
Alternatives and similar repositories for autoredteam
Users that are interested in autoredteam are comparing it to the libraries listed below
Sorting:
- PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to a…☆449Updated last year
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆414Updated last month
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆112Updated last year
- Risks and targets for assessing LLMs & LLM vulnerabilities☆33Updated last year
- TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a…☆78Updated 4 months ago
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆70Updated last year
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆377Updated last year
- ☆186Updated last month
- LLM security and privacy☆53Updated last year
- Red-Teaming Language Models with DSPy☆250Updated 11 months ago
- Papers about red teaming LLMs and Multimodal models.☆159Updated 7 months ago
- PAL: Proxy-Guided Black-Box Attack on Large Language Models☆57Updated last year
- ☆50Updated last year
- ☆684Updated 6 months ago
- This repository provides a benchmark for prompt injection attacks and defenses in LLMs☆380Updated 2 months ago
- Implementation of BEAST adversarial attack for language models (ICML 2024)☆92Updated last year
- TAP: An automated jailbreaking method for black-box LLMs☆217Updated last year
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆82Updated 6 months ago
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆183Updated 9 months ago
- A benchmark for prompt injection detection systems.☆154Updated last month
- Adversarial Attacks on GPT-4 via Simple Random Search [Dec 2023]☆43Updated last year
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆177Updated last year
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆98Updated last year
- ☆34Updated last year
- ☆112Updated last month
- Jailbreak artifacts for JailbreakBench☆75Updated last year
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆124Updated last year
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆157Updated 7 months ago
- A prompt injection game to collect data for robust ML research☆66Updated last year
- Fluent student-teacher redteaming☆23Updated last year