threatdeck
Live 14:45 UTC ·

New Technique Medium TD-2026-0079 For AI Eng, AppSec, CISO AI-assisted

Subspace projection removes LoRA backdoors statically but backdoors rebound under few-shot reactivation

A preprint audits subspace-projection defenses against backdoors in third-party LoRA adapters across four Qwen2.5 scales and three architectures. Module-wise rank-1 trigger-difference projection reduced static attack success rate from 60.4% to 0.0% on standard benchmarks. Under 5-sample few-shot reactivation, every evaluated weight-editing defense rebounded to 91.7%-100.0% ASR in one epoch, reaching 100.0% by epoch 2.

Why it matters

Organizations that rely on near-zero static ASR results may believe a backdoor is removed when the weights still retain it. An attacker with a small amount of data could restore a hidden trigger behavior in a defended adapter.

Do this

  1. Do not treat static ASR reduction after weight projection as proof that a backdoor has been removed from a LoRA adapter.
  2. Vet third-party LoRA adapters from their origin and verify integrity before deployment, since projection-based cleanup is not shown to erase the backdoor.
  3. Re-test defended adapters with few-shot fine-tuning reactivation checks before approving them for production use.
  4. Monitor fine-tuning pipelines that accept small user datasets for re-emergence of trigger-linked outputs.

Signals

  • NoCISA KEV
  • 23/100Priority
  • 60%Confidence

Evidence

“static ASR reduction does not imply parameter erasure”

arXiv (AI security papers)

“Under 5-sample few-shot reactivation, every evaluated weight-editing defense rebounds (91.7%-100.0% ASR in 1 epoch for standard projections”

arXiv (AI security papers)

Sources

Affected / related

LoRA backdoor subspace projection defense, Qwen2.5, InternLM2.5

Published 2026-11-09 18:12 UTC · updated 2026-11-12 18:05 UTC · AI-assisted summary, checked against quoted sources · How we score

Following

Follow the vendors, products, AI tools, techniques and actors you care about. Matching stories, CVEs and exploited bugs are marked, a Following tab appears in the feed, and returning visits show what changed. Saved only in this browser.

Presets

Get updates

A personal RSS feed of new stories on everything you follow. Paste it into any feed reader, Slack or Teams RSS app.