chawins / llm-sp
Papers and resources related to the security and privacy of LLMs π€
β496Updated 4 months ago
Alternatives and similar repositories for llm-sp:
Users that are interested in llm-sp 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 Mβ¦β319Updated 3 months ago
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.β148Updated 3 weeks ago
- This repository provides a benchmark for prompt Injection attacks and defensesβ188Updated last week
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873β152Updated 11 months ago
- We jailbreak GPT-3.5 Turboβs safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20β¦β291Updated last year
- Official repo for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Promptsβ483Updated 7 months ago
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]β332Updated 3 weeks ago
- BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks on Large Language Modelsβ134Updated 2 months ago
- A fast + lightweight implementation of the GCG algorithm in PyTorchβ225Updated 2 months ago
- A resource repository for machine unlearning in large language modelsβ377Updated 3 weeks ago
- TAP: An automated jailbreaking method for black-box LLMsβ165Updated 4 months ago
- A curation of awesome tools, documents and projects about LLM Security.β1,186Updated last week
- [USENIX Security 2025] PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Modelsβ140Updated 2 months ago
- Awesome LLM Jailbreak academic papersβ94Updated last year
- β128Updated 7 months ago
- Papers about red teaming LLMs and Multimodal models.β111Updated 5 months ago
- β540Updated 4 months ago
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalβ627Updated 8 months ago
- A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).β1,377Updated this week
- LLM security and privacyβ48Updated 6 months ago
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Promptsβ134Updated 2 months ago
- UP-TO-DATE LLM Watermark paper. π₯π₯π₯β337Updated 4 months ago
- A survey on harmful fine-tuning attack for large language modelβ161Updated last week
- [NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Surveyβ94Updated 8 months ago
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllabilityβ150Updated 4 months ago
- Accepted by IJCAI-24 Survey Trackβ200Updated 8 months ago
- Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel, exciting jailbreak methods on LLMs. It contains papers, codes, dataβ¦β626Updated this week
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decodingβ129Updated 9 months ago
- The official implementation of our NAACL 2024 paper "A Wolf in Sheepβs Clothing: Generalized Nested Jailbreak Prompts can Fool Large Langβ¦β102Updated 3 months ago
- π up-to-date & curated list of awesome Attacks on Large-Vision-Language-Models papers, methods & resources.β271Updated 2 weeks ago