Developing Assurance Cases for Adversarial Robustness and Regulatory Compliance in LLMs

• URL: http://arxiv.org/abs/2410.05304v1
• Date: Fri, 4 Oct 2024 18:14:29 GMT
• Title: Developing Assurance Cases for Adversarial Robustness and Regulatory Compliance in LLMs
• Authors: Tomas Bueno Momcilovic, Dian Balta, Beat Buesser, Giulio Zizzo, Mark Purcell,
• Abstract summary: We develop an approach to developing assurance cases for adversarial robustness and regulatory compliance in large language models (LLMs) We propose a layered framework incorporating guardrails at various stages of deployment, aimed at mitigating these attacks and ensuring compliance with the EU AI Act. We illustrate our method with two exemplary assurance cases, highlighting how different contexts demand tailored strategies to ensure robust and compliant AI systems.
• Score: 1.368472250332885
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper presents an approach to developing assurance cases for adversarial robustness and regulatory compliance in large language models (LLMs). Focusing on both natural and code language tasks, we explore the vulnerabilities these models face, including adversarial attacks based on jailbreaking, heuristics, and randomization. We propose a layered framework incorporating guardrails at various stages of LLM deployment, aimed at mitigating these attacks and ensuring compliance with the EU AI Act. Our approach includes a meta-layer for dynamic risk management and reasoning, crucial for addressing the evolving nature of LLM vulnerabilities. We illustrate our method with two exemplary assurance cases, highlighting how different contexts demand tailored strategies to ensure robust and compliant AI systems.

Related papers

• A Formal Framework for Assessing and Mitigating Emergent Security Risks in Generative AI Models: Bridging Theory and Dynamic Risk Mitigation [0.3413711585591077]
  As generative AI systems, including large language models (LLMs) and diffusion models, advance rapidly, their growing adoption has led to new and complex security risks. This paper introduces a novel formal framework for categorizing and mitigating these emergent security risks. We identify previously under-explored risks, including latent space exploitation, multi-modal cross-attack vectors, and feedback-loop-induced model degradation.
  arXiv  Detail & Related papers  (2024-10-15T02:51:32Z)
• Towards Assuring EU AI Act Compliance and Adversarial Robustness of LLMs [1.368472250332885]
  Large language models are prone to misuse and vulnerable to security threats. The European Union's Artificial Intelligence Act seeks to enforce AI robustness in certain contexts.
  arXiv  Detail & Related papers  (2024-10-04T18:38:49Z)
• Knowledge-Augmented Reasoning for EUAIA Compliance and Adversarial Robustness of LLMs [1.368472250332885]
  The EU AI Act (EUAIA) introduces requirements for AI systems which intersect with the processes required to establish adversarial robustness. This paper presents a functional architecture that focuses on bridging the two properties. We aim to support developers and auditors with a reasoning layer based on knowledge augmentation.
  arXiv  Detail & Related papers  (2024-10-04T18:23:14Z)
• Compromising Embodied Agents with Contextual Backdoor Attacks [69.71630408822767]
  Large language models (LLMs) have transformed the development of embodied intelligence. This paper uncovers a significant backdoor security threat within this process. By poisoning just a few contextual demonstrations, attackers can covertly compromise the contextual environment of a black-box LLM.
  arXiv  Detail & Related papers  (2024-08-06T01:20:12Z)
• Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs) [17.670925982912312]
  Red-teaming is a technique for identifying vulnerabilities in large language models (LLM) This paper presents a detailed threat model and provides a systematization of knowledge (SoK) of red-teaming attacks on LLMs.
  arXiv  Detail & Related papers  (2024-07-20T17:05:04Z)
• Threat Modelling and Risk Analysis for Large Language Model (LLM)-Powered Applications [0.0]
  Large Language Models (LLMs) have revolutionized various applications by providing advanced natural language processing capabilities. This paper explores the threat modeling and risk analysis specifically tailored for LLM-powered applications.
  arXiv  Detail & Related papers  (2024-06-16T16:43:58Z)
• MirrorCheck: Efficient Adversarial Defense for Vision-Language Models [55.73581212134293]
  We propose a novel, yet elegantly simple approach for detecting adversarial samples in Vision-Language Models. Our method leverages Text-to-Image (T2I) models to generate images based on captions produced by target VLMs. Empirical evaluations conducted on different datasets validate the efficacy of our approach.
  arXiv  Detail & Related papers  (2024-06-13T15:55:04Z)
• Learning diverse attacks on large language models for robust red-teaming and safety tuning [126.32539952157083]
  Red-teaming, or identifying prompts that elicit harmful responses, is a critical step in ensuring the safe deployment of large language models. We show that even with explicit regularization to favor novelty and diversity, existing approaches suffer from mode collapse or fail to generate effective attacks. We propose to use GFlowNet fine-tuning, followed by a secondary smoothing phase, to train the attacker model to generate diverse and effective attack prompts.
  arXiv  Detail & Related papers  (2024-05-28T19:16:17Z)
• 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)
• Data Poisoning for In-context Learning [49.77204165250528]
  In-context learning (ICL) has been recognized for its innovative ability to adapt to new tasks. This paper delves into the critical issue of ICL's susceptibility to data poisoning attacks. We introduce ICLPoison, a specialized attacking framework conceived to exploit the learning mechanisms of ICL.
  arXiv  Detail & Related papers  (2024-02-03T14:20:20Z)
• Visual Adversarial Examples Jailbreak Aligned Large Language Models [66.53468356460365]
  We show that the continuous and high-dimensional nature of the visual input makes it a weak link against adversarial attacks. We exploit visual adversarial examples to circumvent the safety guardrail of aligned LLMs with integrated vision. Our study underscores the escalating adversarial risks associated with the pursuit of multimodality.
  arXiv  Detail & Related papers  (2023-06-22T22:13:03Z)

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.