
redthread
An autonomous red-teaming engine for LLMs. RedThread manages the full security lifecycle: generating adversarial attacks, executing precision…
adversarial-attackai-securitydefensive-tools+7
50

An autonomous red-teaming engine for LLMs. RedThread manages the full security lifecycle: generating adversarial attacks, executing precision…

Analyzes LLM internal states and 100+ attention/probability features to train classifiers that detect document poisoning attacks in RAG systems.

Practical black-box adversarial packet generation against encrypted traffic classification with minimal overhead and full packet recoverability.

Cyber Threat Defense World Modeling

An automated, high-precision zero-shot evaluation pipeline for OpenAI's CLIP model on CIFAR-10. Features 88.80% accuracy, Safetensors security…

AI 驱动的 SOC 仿真平台