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

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

AI agent framework for black-box security testing with autonomous multi-agent orchestration, built-in pentesting tools, and MCP integration for bug…

A lifecycle benchmark for black-box LLM extraction attacks, defenses, and adaptive attacks.

LLM-driven agentic group shilling attack framework that manipulates black-box collaborative-filtering recommender rankings using adaptive multi-role…

Black-box input-stage purification defense that neutralizes backdoor attacks on object detectors via corruption, diffusion reconstruction, and DBSCAN…

Black-box attack framework that hijacks reasoning in agentic retrieval-augmented generation systems by injecting poisoned documents, with support for…

Black-box test whether an LLM chatbot is vulnerable to markdown/HTML exfil (CVE-2025-32711 class). Spins up a sink, sends payloads, renders in…

Red-teaming benchmark and black-box attack framework for evaluating visual misinformation risks in commercial image generators, with 10k false-claim…

Bypass restricted and censored content on AI chat prompts 😈

LLM powered fuzzing via OSS-Fuzz.