XHMY / AutoDefenseLinks
AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
☆55Updated 4 months ago
Alternatives and similar repositories for AutoDefense
Users that are interested in AutoDefense are comparing it to the libraries listed below
Sorting:
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆169Updated 5 months ago
- ☆79Updated last year
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆151Updated 5 months ago
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)☆148Updated 9 months ago
- TAP: An automated jailbreaking method for black-box LLMs☆185Updated 9 months ago
- This repository provides a benchmark for prompt Injection attacks and defenses☆284Updated 2 months ago
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆91Updated 11 months ago
- Agent Security Bench (ASB)☆119Updated 3 months ago
- ☆148Updated last year
- ☆62Updated 9 months ago
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆58Updated 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…☆132Updated 3 weeks ago
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]☆419Updated 5 months ago
- ☆103Updated 7 months ago
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆166Updated 9 months ago
- [arXiv:2311.03191] "DeepInception: Hypnotize Large Language Model to Be Jailbreaker"☆162Updated last year
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆346Updated 8 months ago
- Code to generate NeuralExecs (prompt injection for LLMs)☆22Updated 10 months ago
- [ICLR 2024] The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language M…☆380Updated 8 months ago
- [NeurIPS 2025] BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models☆213Updated this week
- Implementation for "RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content"☆22Updated last year
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆60Updated last year
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆171Updated 2 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆143Updated last year
- [CCS 2024] Optimization-based Prompt Injection Attack to LLM-as-a-Judge☆31Updated this week
- Papers about red teaming LLMs and Multimodal models.☆139Updated 3 months ago
- official implementation of [USENIX Sec'25] StruQ: Defending Against Prompt Injection with Structured Queries☆46Updated last month
- [ICLR24] Official Repo of BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models☆38Updated last year
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆70Updated last month
- [ICLR 2025] Dissecting adversarial robustness of multimodal language model agents☆106Updated 7 months ago