gitkolento / SecProbeLinks
SecProbe:任务驱动式大模型安全能力评测系统
☆14Updated 6 months ago
Alternatives and similar repositories for SecProbe
Users that are interested in SecProbe are comparing it to the libraries listed below
Sorting:
- JailBench:大型语言模型越狱攻击风险评测中文数据集 [PAKDD 2025]☆98Updated 3 months ago
- ☆13Updated 3 weeks ago
- ☆36Updated last month
- ☆26Updated 8 months ago
- Safety at Scale: A Comprehensive Survey of Large Model Safety☆173Updated 4 months ago
- 复旦白泽大模型安全基准测试集(2024年夏季版)☆38Updated 10 months ago
- Agent Security Bench (ASB)☆89Updated last week
- [USENIX Security'24] Official repository of "Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise a…☆97Updated 8 months ago
- Code for paper "The Philosopher’s Stone: Trojaning Plugins of Large Language Models"☆18Updated 9 months ago
- [USENIX Security 2025] PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models☆163Updated 4 months ago
- ☆66Updated 11 months ago
- ☆45Updated last year
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆158Updated 2 months ago
- 针对大语言模型的对抗性攻击总结☆29Updated last year
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆130Updated 2 months ago
- BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models☆167Updated this week
- SC-Safety: 中文大模型多轮对抗安全基准☆137Updated last year
- ☆58Updated 6 months ago
- ☆17Updated last month
- The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Lang…☆115Updated 5 months ago
- ☆139Updated 9 months ago
- The most comprehensive and accurate LLM jailbreak attack benchmark by far☆19Updated 3 months ago
- Official github repo for SafetyBench, a comprehensive benchmark to evaluate LLMs' safety. [ACL 2024]☆225Updated last year
- [NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey☆103Updated 10 months ago
- ☆72Updated 7 months ago
- ☆34Updated 8 months ago
- [arXiv:2311.03191] "DeepInception: Hypnotize Large Language Model to Be Jailbreaker"☆149Updated last year
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)☆139Updated 6 months ago
- ☆21Updated last year
- LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models☆20Updated 3 weeks ago