Prevented is Not Protected: What Attack Success Rate Hides about RAG

Reported by arXiv cs.CR (Chahana Dahal, Zuobin Xiong)

Summary by Cyber Security News2 Nov 2026, 06:00 CET

About this summary. This is a short excerpt from the description that arXiv cs.CR published with its article. Cyber Security News did not report or verify the underlying story. Read the original: https://arxiv.org/abs/2610.40742

arXiv:2610.40742v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) is vulnerable to knowledge poisoning, where adversaries manipulate retrieved evidence to influence model outputs. Existing defenses are primarily evaluated using attack success rate (ASR), which obscures defense-induced failures and the mechanisms behind apparent attack prevention.

Read the full article at arXiv cs.CR →

Source attribution: headline and facts are from arXiv cs.CR (arxiv.org). Summary method: excerpt of the source description. See our source attribution policy.

Related coverage

What Malware Actually Does: An Empirical Analysis of Post-Infection Behavior Across Malware Families

Monitoring AI agent sessions: Leveraging embedding models to aid threat hunting and attack discovery workflows

Qwen 3.8 27B on my laptop can interpret model weights, too

Agentic Backdoors via Pretraining Poisoning

Scan Before You Install: Detecting and Mitigating Local and Composite Vulnerabilities in Skills

GitHub Octoverse 2026