RESEARCHMonitorWATCHLIST
Can LLMs Write Backdoors? An Empirical Security Study of Weight-Space Programming
arXiv cs.LG — Machine Learning
Factual evidence
What the source reports
Researchers demonstrated that LLMs using weight-space programming can inject backdoors directly into target model weights without gradient training.
Inspect the evidence
- Inclusion basis
- Enterprise AI
- Publisher and source type
- arXiv cs.LG — Machine Learning · RESEARCH
- Published by source
- 16 November 2026
- Collected by OneBench
- 17 Nov 2026, 02:01 UK
Stored source excerpt
arXiv:2611.17395v1 Announce Type: cross Abstract: Recent advances in weight-space programming (WSP) have demonstrated that large language models (LLMs) can directly inspect and modify neural network…
Short excerpt from the collected text, not the full source. Use the source link to read it in context.
The factual summary is a OneBench synthesis, not a quotation or independent verification. Collection time is not publication time. Open the source for its full context; related reporting can share the same underlying announcement.