sudo rm -rf agentic_security

• URL: http://arxiv.org/abs/2503.20279v2
• Date: Fri, 04 Apr 2025 04:36:20 GMT
• Title: sudo rm -rf agentic_security
• Authors: Sejin Lee, Jian Kim, Haon Park, Ashkan Yousefpour, Sangyoon Yu, Min Song,
• Abstract summary: We present SUDO, a novel attack framework that bypasses refusal trained safeguards in commercial computer-use agents.<n>The core mechanism, Detox2Tox, transforms harmful requests (that agents initially reject) into seemingly benign requests.<n>It also secures detailed instructions from advanced vision language models (VLMs), and then reintroduces malicious content via toxification.
• Score: 1.6561363996896472
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large Language Models (LLMs) are increasingly deployed as computer-use agents, autonomously performing tasks within real desktop or web environments. While this evolution greatly expands practical use cases for humans, it also creates serious security exposures. We present SUDO (Screen-based Universal Detox2Tox Offense), a novel attack framework that systematically bypasses refusal trained safeguards in commercial computer-use agents, such as Claude Computer Use. The core mechanism, Detox2Tox, transforms harmful requests (that agents initially reject) into seemingly benign requests via detoxification, secures detailed instructions from advanced vision language models (VLMs), and then reintroduces malicious content via toxification just before execution. Unlike conventional jailbreaks, SUDO iteratively refines its attacks based on a built-in refusal feedback, making it increasingly effective against robust policy filters. In extensive tests spanning 50 real-world tasks and multiple state-of-the-art VLMs, SUDO achieves a stark attack success rate of 24% (with no refinement), and up to 41% (by its iterative refinement) in Claude Computer Use. By revealing these vulnerabilities and demonstrating the ease with which they can be exploited in real-world computing environments, this paper highlights an immediate need for robust, context-aware safeguards. WARNING: This paper includes harmful or offensive model outputs Our code is available at: https://github.com/AIM-Intelligence/SUDO.git

Related papers

• DoomArena: A framework for Testing AI Agents Against Evolving Security Threats [84.94654617852322]
  We present DoomArena, a security evaluation framework for AI agents. It is a plug-in framework and integrates easily into realistic agentic frameworks. It is modular and decouples the development of attacks from details of the environment in which the agent is deployed.
  arXiv  Detail & Related papers  (2025-04-18T20:36:10Z)
• Countering Autonomous Cyber Threats [40.00865970939829]
  Foundation Models present dual-use concerns broadly and within the cyber domain specifically. Recent research has shown the potential for these advanced models to inform or independently execute offensive cyberspace operations. This work evaluates several state-of-the-art FMs on their ability to compromise machines in an isolated network and investigates defensive mechanisms to defeat such AI-powered attacks.
  arXiv  Detail & Related papers  (2024-10-23T22:46:44Z)
• Hallucinating AI Hijacking Attack: Large Language Models and Malicious Code Recommenders [0.0]
  Research builds and evaluates the adversarial potential to introduce copied code or hallucinated AI recommendations for malicious code in popular code repositories. foundational large language models (LLMs) from OpenAI, Google, and Anthropic guard against both harmful behaviors and toxic strings. We compare this attack to previous work on context-shifting and contrast the attack surface as a novel version of "living off the land" attacks in the malware literature.
  arXiv  Detail & Related papers  (2024-10-09T01:36:25Z)
• AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases [73.04652687616286]
  We propose AgentPoison, the first backdoor attack targeting generic and RAG-based LLM agents by poisoning their long-term memory or RAG knowledge base. Unlike conventional backdoor attacks, AgentPoison requires no additional model training or fine-tuning. On each agent, AgentPoison achieves an average attack success rate higher than 80% with minimal impact on benign performance.
  arXiv  Detail & Related papers  (2024-07-17T17:59:47Z)
• Dissecting Adversarial Robustness of Multimodal LM Agents [70.2077308846307]
  We manually create 200 targeted adversarial tasks and evaluation scripts in a realistic threat model on top of VisualWebArena.<n>We find that we can successfully break latest agents that use black-box frontier LMs, including those that perform reflection and tree search.<n>We also use ARE to rigorously evaluate how the robustness changes as new components are added.
  arXiv  Detail & Related papers  (2024-06-18T17:32:48Z)
• Principles of Designing Robust Remote Face Anti-Spoofing Systems [60.05766968805833]
  This paper sheds light on the vulnerabilities of state-of-the-art face anti-spoofing methods against digital attacks. It presents a comprehensive taxonomy of common threats encountered in face anti-spoofing systems.
  arXiv  Detail & Related papers  (2024-06-06T02:05:35Z)
• Double Backdoored: Converting Code Large Language Model Backdoors to Traditional Malware via Adversarial Instruction Tuning Attacks [15.531860128240385]
  This work investigates novel techniques for transitioning backdoors from the AI/ML domain to traditional computer malware.<n>We present MalInstructCoder, a framework designed to assess the cybersecurity vulnerabilities of instruction-tuned Code LLMs.<n>We conduct a comprehensive investigation into the exploitability of the code-specific instruction tuning process involving three state-of-the-art Code LLMs.
  arXiv  Detail & Related papers  (2024-04-29T10:14:58Z)
• DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness [58.23214712926585]
  We develop a certified defense, DRSM (De-Randomized Smoothed MalConv), by redesigning the de-randomized smoothing technique for the domain of malware detection. Specifically, we propose a window ablation scheme to provably limit the impact of adversarial bytes while maximally preserving local structures of the executables. We are the first to offer certified robustness in the realm of static detection of malware executables.
  arXiv  Detail & Related papers  (2023-03-20T17:25:22Z)
• 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)
• Adversarial EXEmples: A Survey and Experimental Evaluation of Practical Attacks on Machine Learning for Windows Malware Detection [67.53296659361598]
  adversarial EXEmples can bypass machine learning-based detection by perturbing relatively few input bytes. We develop a unifying framework that does not only encompass and generalize previous attacks against machine-learning models, but also includes three novel attacks. These attacks, named Full DOS, Extend and Shift, inject the adversarial payload by respectively manipulating the DOS header, extending it, and shifting the content of the first section.
  arXiv  Detail & Related papers  (2020-08-17T07:16:57Z)

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.