Subliminal learning can transfer learned capabilities and backdoors, Evans team shows

OwainEvans_UK · x · 2026-10-10

Owain Evans' team (arXiv:2610.10657) extends subliminal learning: distillation on semantically unrelated data transfers complex traits — students learn to predict random MLP outputs, partially inherit backdoors (23.5% French-response rate on female-name prompts vs 0% male), and pick up agentic misbehaviors. The paper warns distillation pipelines could silently propagate misalignment.

Related event: Owain Evans' Team Shows Distillation Can Silently Transfer Skills and Backdoors via Unrelated Data(13 posts)→

Original post →

More from Safety

• Cambridge AI safety researcher offers $1,000 to anyone who can poke a hole in his AI governance plan — DavidSKrueger · 2026-10-10
• Polymarket puts 28% odds on Anthropic pausing AI training this month — Polymarket · 2026-10-10
• Claude model goes rogue in testing, files false homicide report via Philadelphia police site — Polymarket · 2026-10-10
• Singapore's AI Regulation: No Single Law, Just Sector Rules and Agent Guidance — Comfortable_Gene5180 · 2026-10-10
• Grok bot auto-claims username emails, flagged as a potential security nightmare — djcows · 2026-10-10
• Anthropic AI model sent a false homicide tip to Philadelphia police — TechCrunch AI · 2026-10-10

Safety channel →