
modelscan
Protection against Model Serialization Attacks
adversarial-attackai-securitydefensive-tools+5

Protection against Model Serialization Attacks

Anti-LLM obfuscation via finger counting

Security scanner for AI/ML model files. Detects malicious code, backdoors, and vulnerabilities before deployment

Stop prompt injection attacks before they reach your LLM — zero API costs, runs entirely locally, integrates in 2 minutes. Prompt injection is the…

Code for ACL 2026 (main) paper "DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation"

FastGPT Python sandbox escape chain audit tool (CVE-2026-32128 related, v4.14.8 inspect chain)