Episode

A deep dive on AI model distillation attacks

Podcast
Risky Business Features
Published
Apr 29, 2026
Duration seconds
4328
Processing state
not_requested
Canonical source
https://risky.biz/RBFEATURES17/
Audio
https://dts.podtrac.com/redirect.mp3/media3.risky.biz/RBFEATURES17.mp3
JSON
/v1/public/podcasts/risky-business-features-7716365/episodes/a-deep-dive-on-ai-model-distillation-attacks
Markdown
/podcast/risky-business-features-7716365/a-deep-dive-on-ai-model-distillation-attacks.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/risky-business-features-7716365/episodes/a-deep-dive-on-ai-model-distillation-attacks/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/risky-business-features-7716365/a-deep-dive-on-ai-model-distillation-attacks.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

In this solo episode of Risky Business Features James Wilson explores how distillation techniques are both a legitimate way to train smaller models, as well as a way to steal model capabilities. It’s not just a problem for frontier labs! Any LLM-based product could have its competitive advantage stolen through these attacks. James covers: High-level concept of distillation Why it matters including close/open-weight/open-source explanation Types of distillation and the prompts used The distillation pipeline end to end Distillation at scale and mitigation techniques Hardware resource constraints for distillation