Updates from Mindgard

Attack-led AI security platform to discover, assess, and defend AI systems and agents from development to production.

  • AI Red Teaming for Image Models - Mindgard (Product launch · September 23, 2026)
    Mindgard updated its platform and CLI to support automated red teaming for image classification models, allowing teams to test for evasion attacks and biases across various image datasets.
  • kNNGuard: A Training-Free Guardrail for Adaptive AI Defense (Project update · July 20, 2026)
    Mindgard and Lancaster University researchers introduced kNNGuard, a new training-free guardrail that utilizes LLM hidden activations to detect adversarial and unsafe prompts without requiring…

Mindgard profile