cve-bench
giovannigatti/cve-benchA benchmark for evaluating AI agents on fixing real-world security vulnerabilities.
ai-securitycode-analysisdevsecops+6
154 months ago
giovannigatti/cve-benchA benchmark for evaluating AI agents on fixing real-world security vulnerabilities.
xueboqiu/prohunterGraph-based threat detection system using inexact graph vector matching to compare threat graphs with CTI-derived attack query graphs for automated…
andyshaw01/poisoncraftThis repository provides the official implementation of POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models.
fabriziosalmi/aimpA serverless networking protocol designed for resilient state synchronization between autonomous agents in fragmented, low-bandwidth networks
rin449/bhpaiMulti-format malware analysis platform combining a stealth Ring-3 Windows sandbox, static PE/PDF analyzers, ransomware key recovery, and an AI…
q-rz/saffronInference scaling for LLM safety assurance
davidc1212/crawRobust audio watermarking framework embedding binary messages into magnitude spectrograms, with differentiable attack simulation, Q-Former pooling,…
clearlotus-git/cve-2024-37054-pocProof-of-concept and research repository for CVE-2024-37054, an unsafe deserialization flaw in MLflow PyFunc model loading that can lead to remote…
aniketkarne/aco-prompt-shieldStop prompt injection attacks before they reach your LLM — zero API costs, runs entirely locally, integrates in 2 minutes. Prompt injection is the…
buter-chkalova/rvbbitsafeA next-generation multi-echelon anti-ransomware fortress for Windows, combining hypervisor, eBPF, AI deception, and hardware-enforced security.
liuz233/hardeResearch code for HARDE, an agent harness that probes and adaptively optimizes components for runtime risk detection and execution control across…
ml-security-research-lab/cachetrapResearch code for a gray-box trojan attack that flips a single KV-cache bit in fine-tuned LLM classifiers and measures per-class attack success rate.
sec5gloc/sec5glocAdversary-resilient deep learning architecture for secure 5G indoor localization, combining CNN and multi-head attention to defend against signal…
euph00/zoneclaw-codeBenchmark and defense code for persistent memory attacks on OpenClaw-style computer-use agents, with memory-zoning mitigation, attack scenarios, and…
usama1002/deleting-the-traceExperiments for control-token chain-of-thought suppression and parser-leniency attacks on tool-using LLM agents
shuangliangx/learning-to-detectDetects unknown jailbreak attacks in large vision-language models using hidden state analysis and autoencoders, with training and evaluation…
c2a2-at-florida-atlantic-university/gr-physecGNU Radio module for physical layer security using deep learning channel fingerprinting, feature quantization, and SHA3-512 key generation from SDR…
vinsontang1/dcvdThe code in "DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization"