LeakGauge
yeasen-z/leakgaugeDetects LLM context-leakage attacks by training lightweight behavior probes on log-probabilities, with vLLM offline/server detection pipelines.
adversarial-attackai-securityanomaly-detection+2
yeasen-z/leakgaugeDetects LLM context-leakage attacks by training lightweight behavior probes on log-probabilities, with vLLM offline/server detection pipelines.
chanwoochoi316/kidnapragBlack-box attack framework that hijacks reasoning in agentic retrieval-augmented generation systems by injecting poisoned documents, with support for…
promptfoo/promptfooTest your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and…
cleverhans-lab/cleverhansAn adversarial example library for constructing attacks, building defenses, and benchmarking both
zhengxr930/malevalOfficial code for the ISSTA 2026 paper: Is "Knowing It’s Malicious" Enough? Evaluating LLMs for Fine-Grained Malware Behavior Auditing
sevuldet/sevuldetA Semantics-Enhanced Learnable Vulnerability Detector
alegrey91/vex8sSuppress vulnerabilities applying Kubernetes context to scans
roxanne_ardary/emailxposeEmailXpose is an open source AI-powered email security system that detects phishing, spam, scams, malware, and social engineering attacks. It goes…
aloshdenny/claude-awmEvades LLM text watermarks by injecting Unicode variation selectors; includes the SynthID generator, mean-g detector, normalization defenses, and…
digicred-oss/caos-osCustomer Assurance Operating System. Answer the security questionnaires your customers send you, once.
beenuar/aisocOpen-source AI-powered Security Operations Center — alert fusion, purple-team drills, agent-assisted triage, MITRE ATT&CK investigation.…
pandaadir05/ghostDetects process injection and memory manipulation used by malware. Finds RWX regions, shellcode patterns, API hooks, thread hijacking, and process…
avalz/waf-a-moleA guided mutation-based fuzzer for ML-based Web Application Firewalls
poppopjmp/vmdragonslayerMulti-engine framework for unpacking and analyzing VM-protected binaries using dynamic taint tracking, symbolic execution, pattern classification,…
alainnothere/llm-circuit-finderI replicated Ng's RYS method and found that duplicating 3 specific layers in Qwen2.5-32B boosts reasoning by 17% and duplicating layers 12-14 in…
lt-asset/resymFor our CCS24 paper 🏆 "ReSym: Harnessing LLMs to Recover Variable and Data Structure Symbols from Stripped Binaries" by Danning Xie, Zhuo Zhang, Nan…
ahaggard2013/binaryninja-ollamaPlugin for Binary Ninja that integrates local Ollama models to rename functions and variables in decompiled HLIL code, preserving privacy by keeping…