paper-with-me

Papers

Developing Assurance Cases for Adversarial Robustness and Regulatory Compliance in LLMs

2024-10-04 · Tomas Bueno Momcilovic, Dian Balta, Beat Buesser, Giulio Zizzo, Mark Purcell

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.

📄 PDF Abstract BibTeX arXiv:2410.05304

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial RobustnessManagement

Similar Papers 제목 키워드 기반

Towards Assuring EU AI Act Compliance and Adversarial Robustness of LLMs

2024-10-04 · Tomas Bueno Momcilovic, Beat Buesser, Giulio Zizzo, Mark Purcell 외

Large language models are prone to misuse and vulnerable to security threats, raising significant safety and security concerns. The European Union's Artificial Intelligence Act seeks to enforce AI robustness in certain c…

Adversarial Robustness

Autonomy and Safety Assurance in the Early Development of Robotics and Autonomous Systems

2025-01-30 · Dhaminda B. Abeywickrama, Michael Fisher, Frederic Wheeler, Louise Dennis

This report provides an overview of the workshop titled Autonomy and Safety Assurance in the Early Development of Robotics and Autonomous Systems, hosted by the Centre for Robotic Autonomy in Demanding and Long-Lasting E…

I came, I saw, I certified: some perspectives on the safety assurance of cyber-physical systems

2024-01-30 · Mithila Sivakumar, Alvine B. Belle, Kimya Khakzad Shahandashti, Oluwafemi Odu 외

The execution failure of cyber-physical systems (e.g., autonomous driving systems, unmanned aerial systems, and robotic systems) could result in the loss of life, severe injuries, large-scale environmental damage, proper…

Autonomous Driving

A framework for assuring the accuracy and fidelity of an AI-enabled Digital Twin of en route UK airspace

2026-01-06 · Adam Keane, Nick Pepper, Chris Burr, Amy Hodgkin 외 arxiv

Digital Twins combine simulation, operational data and Artificial Intelligence (AI), and have the potential to bring significant benefits across the aviation industry. Project Bluebird, an industry-academic collaboration…

Knowledge-Augmented Reasoning for EUAIA Compliance and Adversarial Robustness of LLMs

2024-10-04 · Tomas Bueno Momcilovic, Dian Balta, Beat Buesser, Giulio Zizzo 외

The EU AI Act (EUAIA) introduces requirements for AI systems which intersect with the processes required to establish adversarial robustness. However, given the ambiguous language of regulation and the dynamicity of adve…

Adversarial Robustness