LLM-DRA / DRALinks
[USENIX Security'24] Official repository of "Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction"
☆109Updated last year
Alternatives and similar repositories for DRA
Users that are interested in DRA are comparing it to the libraries listed below
Sorting:
- Agent Security Bench (ASB)☆137Updated 3 weeks ago
- Official repo for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts☆533Updated last year
- ☆36Updated last year
- JailBench:大型语言模型越狱攻击风险评测中文数据集 [PAKDD 2025]☆135Updated 7 months ago
- ☆42Updated 8 months ago
- Code for paper "The Philosopher’s Stone: Trojaning Plugins of Large Language Models"☆25Updated last year
- Safety at Scale: A Comprehensive Survey of Large Model Safety☆200Updated 8 months ago
- ☆16Updated 3 months ago
- 🔥🔥🔥 Detecting hidden backdoors in Large Language Models with only black-box access☆45Updated 4 months ago
- ☆26Updated last year
- Awesome Jailbreak, red teaming arxiv papers (Automatically Update Every 12th hours)☆70Updated this week
- ☆65Updated 10 months ago
- [arXiv:2311.03191] "DeepInception: Hypnotize Large Language Model to Be Jailbreaker"☆164Updated last year
- ☆24Updated 2 months ago
- Consuming Resrouce via Auto-generation for LLM-DoS Attack under Black-box Settings☆17Updated last month
- ☆46Updated last year
- 复旦白泽大模型安全基准测试集(2024年夏季版)☆48Updated last year
- An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)☆102Updated 9 months ago
- [USENIX Security '24] An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities agai…☆52Updated 7 months ago
- [USENIX Security 2025] PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models☆209Updated 8 months ago
- TAP: An automated jailbreaking method for black-box LLMs☆194Updated 10 months ago
- ☆85Updated last year
- ☆108Updated 8 months ago
- AI Model Security Reading Notes☆43Updated 7 months ago
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆64Updated last year
- The official repository of the paper "The Digital Cybersecurity Expert: How Far Have We Come?" presented in IEEE S&P 2025☆23Updated 5 months ago
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆172Updated 6 months ago
- ☆82Updated last month
- The official repository for guided jailbreak benchmark☆24Updated 3 months ago
- S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models☆99Updated 2 weeks ago