Research

Watch · narrated walkthroughs

Multimodal Injection: Payloads in Pixels and Audio

The instruction that hijacks an agent need not be text. Images, audio, and documents are first-class injection channels, and the model's own perception is the vulnerability. This threat lab extends the indirect-injection threat model to non-text modalities: adversarial and steganographic image payloads, audio that transcribes to attacker instructions, invisible-text and OCR document channels, and the provenance and sanitization controls that trust-tag perceptual inputs — each paired with a hardening. Grounded in the primary cross-modal injection and adversarial-audio literature.

Murali Chillakuru·5 episodes
  1. 1
  2. 2
  3. 3
  4. 4
  5. 5