SecondSourceJudgment rebuilt from primary sources

A Microsoft Research preprint reports that a backdoor can be planted in the weights of a model used by AI agents without retraining, by rewriting fewer than ten neurons that normally stay inactive.

Concept illustration: a beige board on dark legs holds a sheet of paper with a curled lower-left corner, topped by a black band lettered MICROSOFT, with a square of red, green, blue and yellow tiles to the left of the word; on the sheet sit two grids of white squares, five rows of seven, each on a base lettered WEIGHTS, and in the right grid the four right-hand squares of the middle row are covered by a brick-red bar with a black bug icon, from which a black cord runs down the right side to a black tag lettered BACKDOOR in the lower-right corner. A ruler-like strip with tick marks runs along the board's bottom edge. Printed on the image: Microsoft Research reports rewriting a few dormant neurons can plant a backdoor without retraining.

The attacker the paper assumes is someone who can modify the model file before deployment, such as a third party distributing fine-tuned versions on a public model hub. The detection method the authors propose has been tried on only 66 model files (arXiv 2611.15118, 2026-11-11). How we checked →

Source and checks

This item ran in the brief of Nov 15, 2026, alongside 9 other items. How we checked it, the quote checks and what was still missing that day are on that issue's How we checked page.

Cite this item

SecondSource (2026). "A Microsoft Research preprint reports that a backdoor can be planted in the weights of a model used by AI agents without retraining, by rewriting fewer than ten neurons that normally stay inactive.." https://secondsource.io/en/research/2026-11-15-3/. Accessed access date.