
bordair-detector
Two-stage prompt-injection and jailbreak detector: regex gates plus a quantised DeBERTa-v3 ONNX classifier, with image, document, and audio support.…
adversarial-attackai-securitycode-analysis+5

Two-stage prompt-injection and jailbreak detector: regex gates plus a quantised DeBERTa-v3 ONNX classifier, with image, document, and audio support.…

Intentionally vulnerable machine learning model for hands-on security training. Explore common ML vulnerabilities, adversarial attacks, and defensive…

Structured challenge repository offering bounties for breaking a neural-network-based random number generator validated against NIST SP 800-22 and SP…

Memory-free continual learning framework for malware classification using mode connectivity-based interpolation. Supports class-incremental and…