Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System

• URL: http://arxiv.org/abs/2502.11358v1
• Date: Mon, 17 Feb 2025 02:15:46 GMT
• Title: Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System
• Authors: Ziyou Jiang, Mingyang Li, Guowei Yang, Junjie Wang, Yuekai Huang, Zhiyuan Chang, Qing Wang,
• Abstract summary: Information theft attacks pose a significant risk to Large Language Model (LLM) tool-learning systems.<n>We propose AutoCMD, a dynamic attack comment generation approach for information theft attacks in LLM tool-learning systems.
• Score: 13.23705767032468
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Information theft attacks pose a significant risk to Large Language Model (LLM) tool-learning systems. Adversaries can inject malicious commands through compromised tools, manipulating LLMs to send sensitive information to these tools, which leads to potential privacy breaches. However, existing attack approaches are black-box oriented and rely on static commands that cannot adapt flexibly to the changes in user queries and the invocation chain of tools. It makes malicious commands more likely to be detected by LLM and leads to attack failure. In this paper, we propose AutoCMD, a dynamic attack comment generation approach for information theft attacks in LLM tool-learning systems. Inspired by the concept of mimicking the familiar, AutoCMD is capable of inferring the information utilized by upstream tools in the toolchain through learning on open-source systems and reinforcement with target system examples, thereby generating more targeted commands for information theft. The evaluation results show that AutoCMD outperforms the baselines with +13.2% $ASR_{Theft}$, and can be generalized to new tool-learning systems to expose their information leakage risks. We also design four defense methods to effectively protect tool-learning systems from the attack.

Related papers

• Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction [68.6543680065379]
  Large language models (LLMs) are vulnerable to prompt injection attacks. We propose a novel defense method that leverages, rather than suppresses, the instruction-following abilities of LLMs.
  arXiv  Detail & Related papers  (2025-04-29T07:13:53Z)
• From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection [11.300387488829035]
  Tool-calling has changed Large Language Model (LLM) applications by integrating external tools.<n>We present ToolCommander, a novel framework designed to exploit vulnerabilities in LLM tool-calling systems through adversarial tool injection.
  arXiv  Detail & Related papers  (2024-12-13T15:15:24Z)
• Extracting Unlearned Information from LLMs with Activation Steering [46.16882599881247]
  Unlearning has emerged as a solution to remove sensitive knowledge from models after training. We propose activation steering as a method for exact information retrieval from unlearned models. Our results demonstrate that exact information retrieval from unlearned models is possible, highlighting a severe vulnerability of current unlearning techniques.
  arXiv  Detail & Related papers  (2024-11-04T21:42:56Z)
• Imprompter: Tricking LLM Agents into Improper Tool Use [35.255462653237885]
  Large Language Model (LLM) Agents are an emerging computing paradigm that blends generative machine learning with tools such as code interpreters, web browsing, email, and more generally, external resources. We contribute to the security foundations of agent-based systems and surface a new class of automatically computed obfuscated adversarial prompt attacks.
  arXiv  Detail & Related papers  (2024-10-19T01:00:57Z)
• SecAlign: Defending Against Prompt Injection with Preference Optimization [52.48001255555192]
  Adrial prompts can be injected into external data sources to override the system's intended instruction and execute a malicious instruction.<n>We propose a new defense called SecAlign based on the technique of preference optimization.<n>Our method reduces the success rates of various prompt injections to around 0%, even against attacks much more sophisticated than ones seen during training.
  arXiv  Detail & Related papers  (2024-10-07T19:34:35Z)
• Are you still on track!? Catching LLM Task Drift with Activations [55.75645403965326]
  Task drift allows attackers to exfiltrate data or influence the LLM's output for other users. We show that a simple linear classifier can detect drift with near-perfect ROC AUC on an out-of-distribution test set. We observe that this approach generalizes surprisingly well to unseen task domains, such as prompt injections, jailbreaks, and malicious instructions.
  arXiv  Detail & Related papers  (2024-06-02T16:53:21Z)
• Threats, Attacks, and Defenses in Machine Unlearning: A Survey [14.03428437751312]
  Machine Unlearning (MU) has recently gained considerable attention due to its potential to achieve Safe AI.<n>This survey aims to fill the gap between the extensive number of studies on threats, attacks, and defenses in machine unlearning.
  arXiv  Detail & Related papers  (2024-03-20T15:40:18Z)
• Attack Prompt Generation for Red Teaming and Defending Large Language Models [70.157691818224]
  Large language models (LLMs) are susceptible to red teaming attacks, which can induce LLMs to generate harmful content. We propose an integrated approach that combines manual and automatic methods to economically generate high-quality attack prompts.
  arXiv  Detail & Related papers  (2023-10-19T06:15:05Z)
• Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection [64.67495502772866]
  Large Language Models (LLMs) are increasingly being integrated into various applications. We show how attackers can override original instructions and employed controls using Prompt Injection attacks. We derive a comprehensive taxonomy from a computer security perspective to systematically investigate impacts and vulnerabilities.
  arXiv  Detail & Related papers  (2023-02-23T17:14:38Z)
• MERLIN -- Malware Evasion with Reinforcement LearnINg [26.500149465292246]
  We propose a method using reinforcement learning with DQN and REINFORCE algorithms to challenge two state-of-the-art malware detection engines. Our method combines several actions, modifying a Windows portable execution file without breaking its functionalities. We demonstrate that REINFORCE achieves very good evasion rates even on a commercial AV with limited available information.
  arXiv  Detail & Related papers  (2022-03-24T10:58:47Z)
• Automating Privilege Escalation with Deep Reinforcement Learning [71.87228372303453]
  In this work, we exemplify the potential threat of malicious actors using deep reinforcement learning to train automated agents. We present an agent that uses a state-of-the-art reinforcement learning algorithm to perform local privilege escalation. Our agent is usable for generating realistic attack sensor data for training and evaluating intrusion detection systems.
  arXiv  Detail & Related papers  (2021-10-04T12:20:46Z)
• Enhanced Adversarial Strategically-Timed Attacks against Deep Reinforcement Learning [91.13113161754022]
  We introduce timing-based adversarial strategies against a DRL-based navigation system by jamming in physical noise patterns on the selected time frames. Our experimental results show that the adversarial timing attacks can lead to a significant performance drop.
  arXiv  Detail & Related papers  (2020-02-20T21:39:25Z)

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.