Deep Research Brings Deeper Harm

• URL: http://arxiv.org/abs/2510.11851v2
• Date: Wed, 22 Oct 2025 20:02:16 GMT
• Title: Deep Research Brings Deeper Harm
• Authors: Shuo Chen, Zonggen Li, Zhen Han, Bailan He, Tong Liu, Haokun Chen, Georg Groh, Philip Torr, Volker Tresp, Jindong Gu,
• Abstract summary: Deep Research (DR) agents built on Large Language Models (LLMs) can perform complex, multi-step research.<n>This is especially concerning in high-stakes and knowledge-intensive domains such as biosecurity.<n>We propose two novel jailbreak strategies: Plan Injection, which injects malicious sub-goals into the agent's plan; and Intent Hijack, which reframes harmful queries as academic research questions.
• Score: 64.71728362573624
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep Research (DR) agents built on Large Language Models (LLMs) can perform complex, multi-step research by decomposing tasks, retrieving online information, and synthesizing detailed reports. However, the misuse of LLMs with such powerful capabilities can lead to even greater risks. This is especially concerning in high-stakes and knowledge-intensive domains such as biosecurity, where DR can generate a professional report containing detailed forbidden knowledge. Unfortunately, we have found such risks in practice: simply submitting a harmful query, which a standalone LLM directly rejects, can elicit a detailed and dangerous report from DR agents. This highlights the elevated risks and underscores the need for a deeper safety analysis. Yet, jailbreak methods designed for LLMs fall short in exposing such unique risks, as they do not target the research ability of DR agents. To address this gap, we propose two novel jailbreak strategies: Plan Injection, which injects malicious sub-goals into the agent's plan; and Intent Hijack, which reframes harmful queries as academic research questions. We conducted extensive experiments across different LLMs and various safety benchmarks, including general and biosecurity forbidden prompts. These experiments reveal 3 key findings: (1) Alignment of the LLMs often fail in DR agents, where harmful prompts framed in academic terms can hijack agent intent; (2) Multi-step planning and execution weaken the alignment, revealing systemic vulnerabilities that prompt-level safeguards cannot address; (3) DR agents not only bypass refusals but also produce more coherent, professional, and dangerous content, compared with standalone LLMs. These results demonstrate a fundamental misalignment in DR agents and call for better alignment techniques tailored to DR agents. Code and datasets are available at https://chenxshuo.github.io/deeper-harm.

Related papers

• The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search [58.8834056209347]
  Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs.<n>We introduce the Correlated Knowledge Attack Agent (CKA-Agent), a dynamic framework that reframes jailbreaking as an adaptive, tree-structured exploration of the target model's knowledge base.
  arXiv  Detail & Related papers  (2025-12-01T07:05:23Z)
• Instruction Boundary: Quantifying Biases in LLM Reasoning under Various Coverage [34.247904738521136]
  We investigate how different instruction formats can either facilitate or mislead LLM reasoning ability.<n>We introduce the concept of Instruction Boundary, which systematically analyzes how different levels of prompt coverage can lead to reasoning biases.<n>We propose BiasDetector, a unified framework that quantifies LLMs' ability to identify sparse labels under different kinds of Instruction Boundary conditions.
  arXiv  Detail & Related papers  (2025-09-24T16:15:26Z)
• Paper Summary Attack: Jailbreaking LLMs through LLM Safety Papers [61.57691030102618]
  We propose a novel jailbreaking method, Paper Summary Attack (llmnamePSA)<n>It synthesizes content from either attack-focused or defense-focused LLM safety paper to construct an adversarial prompt template.<n>Experiments show significant vulnerabilities not only in base LLMs, but also in state-of-the-art reasoning model like Deepseek-R1.
  arXiv  Detail & Related papers  (2025-07-17T18:33:50Z)
• Hoist with His Own Petard: Inducing Guardrails to Facilitate Denial-of-Service Attacks on Retrieval-Augmented Generation of LLMs [8.09404178079053]
  Retrieval-Augmented Generation (RAG) integrates Large Language Models (LLMs) with external knowledge bases, improving output quality while introducing new security risks.<n>Existing studies on RAG vulnerabilities typically focus on exploiting the retrieval mechanism to inject erroneous knowledge or malicious texts, inducing incorrect outputs.<n>In this paper, we uncover a novel vulnerability: the safety guardrails of LLMs, while designed for protection, can also be exploited as an attack vector by adversaries. Building on this vulnerability, we propose MutedRAG, a novel denial-of-service attack that reversely leverages the guardrails to undermine the availability of
  arXiv  Detail & Related papers  (2025-04-30T14:18:11Z)
• Look Before You Leap: Enhancing Attention and Vigilance Regarding Harmful Content with GuidelineLLM [53.79753074854936]
  Large language models (LLMs) are increasingly vulnerable to emerging jailbreak attacks.<n>This vulnerability poses significant risks to real-world applications.<n>We propose a novel defensive paradigm called GuidelineLLM.
  arXiv  Detail & Related papers  (2024-12-10T12:42:33Z)
• Targeting the Core: A Simple and Effective Method to Attack RAG-based Agents via Direct LLM Manipulation [4.241100280846233]
  AI agents, powered by large language models (LLMs), have transformed human-computer interactions by enabling seamless, natural, and context-aware communication.<n>This paper investigates a critical vulnerability: adversarial attacks targeting the LLM core within AI agents.
  arXiv  Detail & Related papers  (2024-12-05T18:38:30Z)
• AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents [84.96249955105777]
  LLM agents may pose a greater risk if misused, but their robustness remains underexplored.<n>We propose a new benchmark called AgentHarm to facilitate research on LLM agent misuse.<n>We find leading LLMs are surprisingly compliant with malicious agent requests without jailbreaking.
  arXiv  Detail & Related papers  (2024-10-11T17:39:22Z)
• F2A: An Innovative Approach for Prompt Injection by Utilizing Feign Security Detection Agents [0.0]
  Large Language Models exhibit blind trust in safety detection agents. This paper proposed an attack named Feign Agent Attack (F2A) Experiments involved various scenarios where fake safety detection results were injected into prompts.
  arXiv  Detail & Related papers  (2024-10-11T12:49:05Z)
• Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification [35.16099878559559]
  Large language models (LLMs) have experienced significant development and are being deployed in real-world applications. We introduce a new type of attack that causes malfunctions by misleading the agent into executing repetitive or irrelevant actions. Our experiments reveal that these attacks can induce failure rates exceeding 80% in multiple scenarios.
  arXiv  Detail & Related papers  (2024-07-30T14:35:31Z)
• The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning [87.1610740406279]
  White House Executive Order on Artificial Intelligence highlights the risks of large language models (LLMs) empowering malicious actors in developing biological, cyber, and chemical weapons. Current evaluations are private, preventing further research into mitigating risk. We publicly release the Weapons of Mass Destruction Proxy benchmark, a dataset of 3,668 multiple-choice questions.
  arXiv  Detail & Related papers  (2024-03-05T18:59:35Z)
• A Chinese Dataset for Evaluating the Safeguards in Large Language Models [46.43476815725323]
  Large language models (LLMs) can produce harmful responses. This paper introduces a dataset for the safety evaluation of Chinese LLMs. We then extend it to two other scenarios that can be used to better identify false negative and false positive examples.
  arXiv  Detail & Related papers  (2024-02-19T14:56:18Z)
• Evil Geniuses: Delving into the Safety of LLM-based Agents [35.49857256840015]
  Large language models (LLMs) have revitalized in large language models (LLMs) This paper delves into the safety of LLM-based agents from three perspectives: agent quantity, role definition, and attack level.
  arXiv  Detail & Related papers  (2023-11-20T15:50:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.