#1ML-based security tools, adversarial machine learning, and AI-powered cyber defense.
Kitploit recommended
zjuwyh/shadowmemDefensive framework that maintains a safety-focused shadow memory to detect and block prompt-injection and long-horizon threats against LLM agents…
norrrrrrr-lyn/wainjectbenchBenchmarking prompt injection detections for web agents.
alex66366/odpureBlack-box input-stage purification defense that neutralizes backdoor attacks on object detectors via corruption, diffusion reconstruction, and DBSCAN…
usama1002/deleting-the-traceExperiments for control-token chain-of-thought suppression and parser-leniency attacks on tool-using LLM agents
resharma/ajarMeasuring Open Privilege in Agent Defenses
bardlaudian/cve-2024-37054Proof-of-concept that poisons MLflow registered models via the REST API, embedding a malicious pickle to trigger RCE when the model is loaded.
selectstar-ai/finred-paperfinance domain specific red-teaming benchmark evaluation rubric
trailofbits/privacyravenPrivacy testing library for deep learning systems, enabling assessment of susceptibility to membership inference, model extraction, and model…
protectai/rebuffMulti-layered prompt injection detector for AI applications using heuristics, LLM-based analysis, vectorDB attack signatures, and canary token leak…
salesforce/merlionEnd-to-end Python framework for time series intelligence, offering anomaly detection, forecasting, change point detection, AutoML, ensembles, and…
certcc/certfuzzThis project contains the source code for the CERT Basic Fuzzing Framework (BFF) and the CERT Failure Observation Engine (FOE).
doubangotelecom/facelivenessdetection-sdk3D Passive Face Liveness Detection (Anti-Spoofing) & Deepfake detection. A single image is needed to compute liveness score. 99,67% accuracy on our…
