mlsanityData to 7 Oct 2026

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

arXiv 2410.09078 ↗First posted 4 Oct 2024cs.CL cs.AI cs.CYcited by 0

On the map: LLM reasoning → Reasoning for agents, planning and code

Abstract (arXiv)

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 adversarial attacks, developers of systems with highly complex models such as LLMs may find their effort to be duplicated without the assurance of having achieved either compliance or robustness. This paper presents a functional architecture that focuses on bridging the two properties, by introducing components with clear reference to their source. Taking the detection layer recommended by the literature, and the reporting layer required by the law, we aim to support developers and auditors with a reasoning layer based on knowledge augmentation (rules, assurance cases, contextual mappings). Our findings demonstrate a novel direction for ensuring LLMs deployed in the EU are both compliant and adversarially robust, which underpin trustworthiness.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 5 of its 19 references that are in the map. First posted on arXiv 4 Oct 2024.

Builds on

5 of 19 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs12 Jan

Other references · 4

  1. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  2. 2023Detecting Language Model Attacks with Perplexitycited by 411
  3. 2024Coercing LLMs to do and reveal (almost) anythingcited by 88
  4. 2021Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needscited by 64

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Safety Compliance: Rethinking LLM Safety Reasoning through the Lens of Compliance
  2. 2026Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety
  3. 2025Adversarial Testing in LLMs: Insights into Decision-Making Vulnerabilities
  4. 2026Consistency of Large Reasoning Models Under Multi-Turn Attacks
  5. 2026Toward Reliable, Safe, and Secure LLMs for Scientific Applications
  6. 2025aiXamine: Simplified LLM Safety and Security
  7. 2025J&H: Evaluating the Robustness of Large Language Models Under Knowledge-Injection Attacks in Legal Domain
  8. 2024Large Language Model Safety: A Holistic Survey