AI45Lab
Built from AI45Lab's public GitHub profile. Not on Take My Repo yet, so there are no posts or updates here.
OpenART is an open-source framework designed to evaluate the safety and robustness of autonomous AI agents in dynamic, long-horizon, and stateful environments. It stress-tests agent runtimes against multi-step state poisoning, privilege escalation, and tool-use vulnerabilities across 10,000+ benchmark scenarios.
SAfactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence
TrinityGuard: A Unified Framework for Safeguarding Multi-Agent Systems
The repository of the paper "REEF: Representation Encoding Fingerprints for Large Language Models," aims to protect the IP of open-source LLMs.
Flames is a highly adversarial benchmark in Chinese for LLM's harmlessness evaluation developed by Shanghai AI Lab and Fudan NLP Group.
[ACL 2025] Data and Code for Paper VLSBench: Unveiling Visual Leakage in Multimodal Safety
[ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion
Code for paper "MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM safety"
[AAAI 2026] Data and Code for Paper IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks
[EMNLP 2025] The code repo of paper "X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Multi-Turn Jailbreaks without Compromising Usability"
DataElf is an intelligent data workflow engine that turns natural-language tasks into secure, extensible, and executable data pipelines.