Developing Assurance Cases for Adversarial Robustness and Regulatory Compliance in LLMs
On the map: LLM safety and security → Jailbreaking
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 14 of its 20 references that are in the map. First posted on arXiv 4 Oct 2024.
Builds on
14 of 20 references.
Closest ancestors · 7
Same direction, newest first
- 2024Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack2 Apr
- 2024Coercing LLMs to do and reveal (almost) anything21 Feb
- 2024How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs12 Jan
- 2023Self-Guard: Empower the LLM to Safeguard Itself24 Oct
- 2023SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks5 Oct
- 2023Detecting Language Model Attacks with Perplexity27 Aug
- 2023Universal and Transferable Adversarial Attacks on Aligned Language Models27 Jul
Other references · 7
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
- 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
- 2022Language Models are Multilingual Chain-of-Thought Reasonerscited by 518
- 2023Identifying the Risks of LM Agents with an LM-Emulated Sandboxcited by 514
- 2023LLM Self Defense: By Self Examination, LLMs Know They Are Being Trickedcited by 226
- 2021Guidance on the Assurance of Machine Learning in Autonomous Systems (AMLAS)cited by 40
- 2024Generative AI in EU Law: Liability, Privacy, Intellectual Property, and Cybersecuritycited by 21
Built on by
Citing papers per year: 2025: 1.
1 paper.