RRTL: Red Teaming Reasoning Large Language Models in Tool Learning

• URL: http://arxiv.org/abs/2505.17106v1
• Date: Wed, 21 May 2025 10:21:19 GMT
• Title: RRTL: Red Teaming Reasoning Large Language Models in Tool Learning
• Authors: Yifei Liu, Yu Cui, Haibin Zhang,
• Abstract summary: The safety of newly emerging reasoning LLMs (RLLMs) in the context of tool learning remains underexplored.<n>We propose RRTL, a red teaming approach specifically designed to evaluate RLLMs in tool learning.<n>We conduct a comprehensive evaluation on seven mainstream RLLMs and uncover three key findings.
• Score: 8.547055998769476
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While tool learning significantly enhances the capabilities of large language models (LLMs), it also introduces substantial security risks. Prior research has revealed various vulnerabilities in traditional LLMs during tool learning. However, the safety of newly emerging reasoning LLMs (RLLMs), such as DeepSeek-R1, in the context of tool learning remains underexplored. To bridge this gap, we propose RRTL, a red teaming approach specifically designed to evaluate RLLMs in tool learning. It integrates two novel strategies: (1) the identification of deceptive threats, which evaluates the model's behavior in concealing the usage of unsafe tools and their potential risks; and (2) the use of Chain-of-Thought (CoT) prompting to force tool invocation. Our approach also includes a benchmark for traditional LLMs. We conduct a comprehensive evaluation on seven mainstream RLLMs and uncover three key findings: (1) RLLMs generally achieve stronger safety performance than traditional LLMs, yet substantial safety disparities persist across models; (2) RLLMs can pose serious deceptive risks by frequently failing to disclose tool usage and to warn users of potential tool output risks; (3) CoT prompting reveals multi-lingual safety vulnerabilities in RLLMs. Our work provides important insights into enhancing the security of RLLMs in tool learning.

Related papers

• R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning [87.30285670315334]
  textbfR1-Searcher is a novel two-stage outcome-based RL approach designed to enhance the search capabilities of Large Language Models.<n>Our framework relies exclusively on RL, without requiring process rewards or distillation for a cold start.<n>Our experiments demonstrate that our method significantly outperforms previous strong RAG methods, even when compared to the closed-source GPT-4o-mini.
  arXiv  Detail & Related papers  (2025-03-07T17:14:44Z)
• Emerging Security Challenges of Large Language Models [6.151633954305939]
  Large language models (LLMs) have achieved record adoption in a short period of time across many different sectors.<n>They are open-ended models trained on diverse data without being tailored for specific downstream tasks.<n>Traditional Machine Learning (ML) models are vulnerable to adversarial attacks.
  arXiv  Detail & Related papers  (2024-12-23T14:36:37Z)
• When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge? [15.318301783084681]
  Large language models (LLMs) can inadvertently learn and retain sensitive information and harmful content during training. We propose a lightweight unlearning framework based on Retrieval-Augmented Generation (RAG) technology. We evaluate our framework through extensive experiments on both open-source and closed-source models, including ChatGPT, Gemini, Llama-2-7b-chat-hf, and PaLM 2.
  arXiv  Detail & Related papers  (2024-10-20T03:51:01Z)
• Cognitive Overload Attack:Prompt Injection for Long Context [39.61095361609769]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in performing tasks without needing explicit retraining. This capability, known as In-Context Learning (ICL), exposes LLMs to adversarial prompts and jailbreaks that manipulate safety-trained LLMs into generating undesired or harmful output. We apply the principles of Cognitive Load Theory in LLMs and empirically validate that similar to human cognition, LLMs also suffer from cognitive overload. We show that advanced models such as GPT-4, Claude-3.5 Sonnet, Claude-3 OPUS, Llama-3-70B-Instruct, Gemini-1.0-Pro, and
  arXiv  Detail & Related papers  (2024-10-15T04:53:34Z)
• Harnessing Large Language Models for Software Vulnerability Detection: A Comprehensive Benchmarking Study [1.03590082373586]
  We propose using large language models (LLMs) to assist in finding vulnerabilities in source code. The aim is to test multiple state-of-the-art LLMs and identify the best prompting strategies. We find that LLMs can pinpoint many more issues than traditional static analysis tools, outperforming traditional tools in terms of recall and F1 scores.
  arXiv  Detail & Related papers  (2024-05-24T14:59:19Z)
• Unveiling the Misuse Potential of Base Large Language Models via In-Context Learning [61.2224355547598]
  Open-sourcing of large language models (LLMs) accelerates application development, innovation, and scientific progress. Our investigation exposes a critical oversight in this belief. By deploying carefully designed demonstrations, our research demonstrates that base LLMs could effectively interpret and execute malicious instructions.
  arXiv  Detail & Related papers  (2024-04-16T13:22:54Z)
• LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error [54.954211216847135]
  Existing large language models (LLMs) only reach a correctness rate in the range of 30% to 60%. We propose a biologically inspired method for tool-augmented LLMs, simulated trial and error (STE) STE orchestrates three key mechanisms for successful tool use behaviors in the biological system: trial and error, imagination, and memory.
  arXiv  Detail & Related papers  (2024-03-07T18:50:51Z)
• ROSE Doesn't Do That: Boosting the Safety of Instruction-Tuned Large Language Models with Reverse Prompt Contrastive Decoding [89.0074567748505]
  We present reverse prompt contrastive decoding (ROSE), a simple-yet-effective method to boost the safety of existing instruction-tuned LLMs without any additional training. Experiments on 6 safety and 2 general-purpose tasks show that, our ROSE not only brings consistent and significant safety improvements (up to +13.8% safety score) upon 5 types of instruction-tuned LLMs, but also benefits the general-purpose ability of LLMs.
  arXiv  Detail & Related papers  (2024-02-19T06:58:42Z)
• ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages [45.16862486631841]
  Tool learning is widely acknowledged as a foundational approach or deploying large language models (LLMs) in real-world scenarios. To fill this gap, we present *ToolSword*, a comprehensive framework dedicated to investigating safety issues linked to LLMs in tool learning.
  arXiv  Detail & Related papers  (2024-02-16T15:19:46Z)
• Supervised Knowledge Makes Large Language Models Better In-context Learners [94.89301696512776]
  Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering. The challenge of improving the generalizability and factuality of LLMs in natural language understanding and question answering remains under-explored. We propose a framework that enhances the reliability of LLMs as it: 1) generalizes out-of-distribution data, 2) elucidates how LLMs benefit from discriminative models, and 3) minimizes hallucinations in generative tasks.
  arXiv  Detail & Related papers  (2023-12-26T07:24:46Z)

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.