Watchtower
AIShield Watchtower automates model and notebook discovery, performing thorough vulnerability scans to identify risks like hard-coded secrets, PII exposure, outdated libraries, serialization attacks, and unsafe custom operations.
Penetration Testing
Mindgard
Continuous security testing of AI across an organization. Our product is a DAST solution that finds and remediates AI vulnerabilities only detectable at run time.
TrojAI Detect
TrojAI Detect secures AI behavior at build time. The AI security platform continuously red teams AI models to find security weaknesses in AI, ML, and GenAI models during model development before they can be exploited.
Recon
Recon runs automated and comprehensive penetration testing attacks on your LLM powered applications, to help protect you from unique security threats and vulnerabilities. It has the ability to run attacks from an attack library, use an agent for completely automated scans or perform human augmented scans using an LLM Agent.
Modelscan
ModelScan is an open source project from Protect AI that scans models to determine if they contain unsafe code.
Cisco AI Validation
Cisco AI Validation assesses AI applications and models for security and safety vulnerabilities. We automatically analyze a model’s risk across hundreds of attack techniques and threat categories so you can defend against them.
Cisco AI Validation Read Post »
Enkrypt AI
Enkrypt AI secures enterprises against generative AI risks with its comprehensive security platform that detects threats, removes vulnerabilities, and monitors the latest insights on security, compliance and AI performance.
Pillar Security
Pillar enables teams to rapidly adopt AI with minimal risk by providing a unified AI security layer across the organization
ZenGuard AI
ZenGuard AI offers a dev-first API platform for the fastest low-latency GenAI guardrails and hassle-free vulnerability testing for AI applications.
