tml-epfl / llm-adaptive-attacks
Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]
☆251Updated last week
Alternatives and similar repositories for llm-adaptive-attacks:
Users that are interested in llm-adaptive-attacks are comparing it to the libraries listed below
- [ICLR 2024] The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language M…☆282Updated last week
- TAP: An automated jailbreaking method for black-box LLMs☆138Updated last month
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]☆277Updated 4 months ago
- A collection of automated evaluators for assessing jailbreak attempts.☆102Updated this week
- Improving Alignment and Robustness with Circuit Breakers☆176Updated 4 months ago
- A fast + lightweight implementation of the GCG algorithm in PyTorch☆164Updated 3 weeks ago
- ☆470Updated last month
- This repository provides implementation to formalize and benchmark Prompt Injection attacks and defenses☆165Updated last week
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal☆402Updated 5 months ago
- Papers about red teaming LLMs and Multimodal models.☆91Updated 2 months ago
- ☆161Updated last year
- Persuasive Jailbreaker: we can persuade LLMs to jailbreak them!☆279Updated 3 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆113Updated 6 months ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆134Updated 8 months ago
- ☆89Updated last year
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆79Updated this week
- Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.☆110Updated 7 months ago
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆131Updated last month
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆90Updated this week
- We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20…☆266Updated 11 months ago
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆66Updated 11 months ago
- The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Lang…☆88Updated last week
- Does Refusal Training in LLMs Generalize to the Past Tense? [ICLR 2025]☆61Updated last week
- An unofficial implementation of AutoDAN attack on LLMs (arXiv:2310.15140)☆32Updated 11 months ago
- ☆78Updated last year
- PAL: Proxy-Guided Black-Box Attack on Large Language Models☆47Updated 5 months ago
- Weak-to-Strong Jailbreaking on Large Language Models☆72Updated 11 months ago
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)☆109Updated 2 months ago
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆55Updated 9 months ago
- PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to a…☆326Updated 11 months ago