Research
Web Fraud Attacks Against LLM-Driven Multi-Agent Systems
Publication date unknown · Discovered aclanthology.org
Page published
Publication date unknown · First observed: 30 Oct 2026
Coverage timeline
Single-source research — one report is available.
Why it matters
Web Fraud Attacks identify malicious-link trust as a potential entry point for broader attacks against LLM-driven multi-agent systems.
“Web Fraud Attacks Against LLM-Driven Multi-Agent Systems” proposes attacks that manipulate web-link structures to exploit multi-agent systems’ trust in malicious links and expand the attack surface. The supplied abstract is truncated, limiting assessment of the mechanism and any experimental results.