AI Secure

Popular repositories Loading

1. DecodingTrust DecodingTrust Public

   A Comprehensive Assessment of Trustworthiness in GPT Models

   Python 318 63

2. AgentPoison AgentPoison Public

   [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"

   Python 250 35

3. DBA DBA Public

   DBA: Distributed Backdoor Attacks against Federated Learning (ICLR 2020)

   Python 207 49

4. DecodingTrust-Agent DecodingTrust-Agent Public

   Python 98 15

5. Certified-Robustness-SoK-Oldver Certified-Robustness-SoK-Oldver Public

   This repo keeps track of popular provable training and verification approaches towards robust neural networks, including leaderboards on popular datasets and paper categorization.

   97 10

6. RedCode RedCode Public

   [NeurIPS'24] RedCode: Risky Code Execution and Generation Benchmark for Code Agents

   Python 92 10