agent/papers/items/2026-2606-14517-from-shield-to-target-denial-of-service-attacks-on-llm-based-agent-guardrails.md

Paper: From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrails

---

type: paper title: "From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrails" authors: Yuguang Zhou, Xunguang Wang, Pingchuan Ma, Zhantong Xue, Zhaoyu Wang, Shuai Wang year: 2026 venue: arXiv url: https://arxiv.org/abs/2606.14517 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-06-12 updated_at: 2026-06-16 status: queued relevance: high topics:

• agent-evaluation
• agent-safety
• computer-use
• multi-agent
• reasoning methods:

benchmarks:

models:

datasets:

• cs.CR
• cs.AI related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 16 collection_queries: agent-evaluation, autonomous-agent-llm

One-line Takeaway

Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.

Why Collected

• matched queries: agent-evaluation, autonomous-agent-llm
• inferred topics: agent-evaluation, agent-safety, computer-use, multi-agent, reasoning
• arXiv categories: cs.CR, cs.AI
• collection score: 16

Review Checklist

• Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
• Does it include a benchmark, dataset, code, or reproducible experimental setup?
• Should it be promoted from queued to skimmed or summarized?

Links

• arXiv: https://arxiv.org/abs/2606.14517