arXiv Machine Learning June 9, 2026 By Xinyu Li, Ronghui Mu, Lin Li, Tianjin Huang, Gaojie Jin

OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents

Read the original on arXiv Machine Learning →

arXiv:2605. 08876v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly deployed as autonomous agents that execute tool-augmented, multi-step tasks, where latency is a critical factor for real-world applications.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 15

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

arXiv:2606. 14517v1 Announce Type: cross Abstract: LLM-based guardrails have emerged as a highly effective defense against prompt injection and jailbreak attacks in autonomous agents.

By Yuguang Zhou, Xunguang Wang, Pingchuan Ma, Zhantong Xue, Zhaoyu Wang, Shuai Wang

llms agents benchmarks safety

arXiv AI

Sep 16

Universal Defenses for Tool-Integrated LLM Agents Against Adversarial Attacks

The paper proposes universal, tool‑based defenses for large language model agents that use external tools, addressing four types of adversarial attacks: direct and indirect prompt injection, memory poisoning, and backdoor attacks. Two main defenses are introduced: Attacker Tool Filtering, which uses anomaly detection to remove suspicious tools, and Normal Tool Recalling, which restores the agent’s original toolset before planning. The authors also add prompt‑based defenses such as Chain‑of‑Thought prompting and self‑reflection, and demonstrate that these methods dramatically lower attack success rates—often to 0%—across multiple open‑source and proprietary LLMs while maintaining or improving task performance.

By Xiaoyan Li, Yunli Wang

llms agents robotics multimodal safety

arXiv AI

Aug 12

REDAgentBench: Executable Red Teaming and Faithful Measurement of LLM Agent Systems

arXiv:2608. 10669v1 Announce Type: new Abstract: Large language model (LLM) agents combine language-based reasoning with external tools to perform complex tasks.

By Zixing Chen, Xingyuan Liu, Jie Zhu, Huaixia Dou, Shuo Jiang, Junhui Li, Lifan Guo, Feng Chen, Chi Zhang

llms agents multimodal benchmarks safety

arXiv AI

Jun 24

AdversaBench: Automated LLM Red-Teaming with Multi-Judge Confirmation and Cross-Model Transferability

arXiv:2606. 24589v1 Announce Type: new Abstract: Scaling adversarial evaluation of large language models requires both a method for generating hard inputs and a reliable way to confirm that resulting failures are real.

By Khanak Khandelwal (Indian Institute of Technology Jodhpur)

llms agents safety

arXiv AI

Jun 2

AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations

arXiv:2606. 02240v1 Announce Type: cross Abstract: Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from integrations (third-party services such as Gmail, Salesforce, or Jira accessed through tool calls) whose response content the user neither writes nor controls.

By Hiskias Dingeto, Will Leeney

llms agents multimodal benchmarks safety

arXiv AI

4d ago

CounterSteer: Suppressing Indirect Prompt Injection with Activation Steering

arXiv:2609.36570v1 Announce Type: cross Abstract: Indirect prompt injection makes an LLM agent treat untrusted retrieved text as instructions. We present CounterSteer, an inference-time defense that...

By Mark Russinovich

llms agents robotics fine-tuning benchmarks

One email a morning, machine-written

Related stories

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

Universal Defenses for Tool-Integrated LLM Agents Against Adversarial Attacks

REDAgentBench: Executable Red Teaming and Faithful Measurement of LLM Agent Systems

AdversaBench: Automated LLM Red-Teaming with Multi-Judge Confirmation and Cross-Model Transferability

AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations

CounterSteer: Suppressing Indirect Prompt Injection with Activation Steering