RESEARCHMonitorNEXT 12 MONTHS
Backdoor in the Loop: Compromising Agentic Search via Malicious Retrievers
arXiv cs.LG — Machine Learning
Factual evidence
What the source reports
Research demonstrates backdoor attacks on retrievers in agentic RAG, manipulating search feedback loops and evading detection.
Inspect the evidence
- Inclusion basis
- Enterprise AI
- Publisher and source type
- arXiv cs.LG — Machine Learning · RESEARCH
- Published by source
- 30 September 2026
- Collected by OneBench
- 1 Oct 2026, 03:02 UK
Stored source excerpt
arXiv:2609.37468v1 Announce Type: cross Abstract: Agentic retrieval-augmented generation (RAG) interleaves reasoning with repeated retrieval, giving the retriever influence over both the evidence an agent observes…
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.