OpenTAI is an open platform where researchers collaborate to accelerate practical Trustworthy AI solutions. We prioritize tools, benchmarks, and platforms over papers, bridging research with real-world impact.
VisionSafety Bench
An Adversarial Evaluation Platform for Vision Models
Our open-source platform provides datasets, algorithms, and tools for scalable adversarial evaluation of vision models. Now available for community use - we welcome your feedback and contributions!
RewardModel Bench
A Reward Model Benchmark for LLM Alignment Evaluation
A reward model benchmark for evaluating the effectiveness of alignment in large language models. The benchmark consists of 49 real-world scenarios and both pairwise and Best-of-N (BoN) evaluations.
VLBreakBench
A Multimodal Jailbreak Benchmark for Vision-Language Models
VLBreakBench evaluates VLMs through two tiers: a base set (1 jailbreak pair per query) and a challenge set (3 pairs per query), covering 12 safety topics and 46 subcategories (916 harmful queries), totaling 3,654 jailbreak samples.
BlackdoorLLM
A comprehensive toolkit (and benchmark) for backdoor attacks on large language models.
taiadv.vision
An open-source toolkit implementing state-of-the-art adversarial attacks and defenses for vision models.
TextFlint
A multilingual robustness evaluation toolkit for natural language processing.
