
LeakGauge
Detects LLM context-leakage attacks by training lightweight behavior probes on log-probabilities, with vLLM offline/server detection pipelines.

Detects LLM context-leakage attacks by training lightweight behavior probes on log-probabilities, with vLLM offline/server detection pipelines.

Local white-box gradient attacks for open-weight LLMs: GCG/PEZ suffix search, layer saliency, weight snapshots, and rank-1 suffix-to-delta fitting…

Customer Assurance Operating System. Answer the security questionnaires your customers send you, once.

Hunting for passwords with deep learning

A Binary Genetic Traits Lexer Framework

LLM powered fuzzing via OSS-Fuzz.

Production AI defense with 7-layer protection: mathematical constraints, object-capability access, distributed O2 consensus, SVETILO ethics. First…

Sec-Gemini is a cutting-edge AI model designed to enhance cybersecurity capabilities and empower defenders in the ongoing battle against cyber…


PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses

The code in "DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization"

QuantumLock is an open-source, quantum-resistant Bitcoin protocol designed to protect digital assets from future quantum computing threats. Featuring…

MCP Server for Ghidra