Machine Unlearning Meets Adversarial Robustness via Constrained Interventions on LLMs

• URL: http://arxiv.org/abs/2510.03567v3
• Date: Thu, 16 Oct 2025 16:42:58 GMT
• Title: Machine Unlearning Meets Adversarial Robustness via Constrained Interventions on LLMs
• Authors: Fatmazohra Rezkellah, Ramzi Dakhmouche,
• Abstract summary: We investigate various constrained optimization formulations that address unlearning of sensitive information and robustness to jail-breaking attacks.<n>We find that the simplest point-wise constraint-based intervention we propose leads to better performance than max-min interventions, while having a lower computational cost.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the increasing adoption of Large Language Models (LLMs), more customization is needed to ensure privacy-preserving and safe generation. We address this objective from two critical aspects: unlearning of sensitive information and robustness to jail-breaking attacks. We investigate various constrained optimization formulations that address both aspects in a \emph{unified manner}, by finding the smallest possible interventions on LLM weights that either make a given vocabulary set unreachable or embed the LLM with robustness to tailored attacks by shifting part of the weights to a \emph{safer} region. Beyond unifying two key properties, this approach contrasts with previous work in that it doesn't require an oracle classifier that is typically not available or represents a computational overhead. Surprisingly, we find that the simplest point-wise constraint-based intervention we propose leads to better performance than max-min interventions, while having a lower computational cost. Comparison against state-of-the-art defense methods demonstrates superior performance of the proposed approach.

Related papers

• OptiLeak: Efficient Prompt Reconstruction via Reinforcement Learning in Multi-tenant LLM Services [14.316936569697738]
  Multi-tenant LLM serving frameworks widely adopt shared Key-Value caches to enhance efficiency.<n>This creates side-channel vulnerabilities enabling prompt leakage attacks.<n>We propose OptiLeak, a reinforcement learning-enhanced framework that maximizes prompt reconstruction efficiency.
  arXiv  Detail & Related papers  (2026-02-24T06:35:22Z)
• PSM: Prompt Sensitivity Minimization via LLM-Guided Black-Box Optimization [0.0]
  This paper introduces a novel framework for hardening system prompts through shield appending.<n>We leverage an LLM-as-optimizer to search the space of possible SHIELDs, seeking to minimize a leakage metric derived from a suite of adversarial attacks.<n>We demonstrate empirically that our optimized SHIELDs significantly reduce prompt leakage against a comprehensive set of extraction attacks.
  arXiv  Detail & Related papers  (2025-11-20T10:25:45Z)
• SecInfer: Preventing Prompt Injection via Inference-time Scaling [54.21558811232143]
  We propose emphSecInfer, a novel defense against prompt injection attacks built on emphinference-time scaling<n>We show that SecInfer effectively mitigates both existing and adaptive prompt injection attacks, outperforming state-of-the-art defenses as well as existing inference-time scaling approaches.
  arXiv  Detail & Related papers  (2025-09-29T16:00:41Z)
• Constrained Entropic Unlearning: A Primal-Dual Framework for Large Language Models [14.321060805197874]
  Large Language Models (LLMs) deployed in real-world settings increasingly face the need to unlearn sensitive, outdated, or proprietary information.<n>Existing unlearning methods formulate forgetting and retention as a regularized trade-off, combining both objectives into a single scalarized loss.<n>We propose a new formulation of LLM unlearning as a constrained optimization problem: forgetting is enforced via a novel logit-margin flattening loss.
  arXiv  Detail & Related papers  (2025-06-05T17:55:23Z)
• One-Shot Safety Alignment for Large Language Models via Optimal Dualization [64.52223677468861]
  This paper presents a perspective of dualization that reduces constrained alignment to an equivalent unconstrained alignment problem. We do so by pre-optimizing a smooth and convex dual function that has a closed form. Our strategy leads to two practical algorithms in model-based and preference-based settings.
  arXiv  Detail & Related papers  (2024-05-29T22:12:52Z)
• Efficient Adversarial Training in LLMs with Continuous Attacks [99.5882845458567]
  Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails. We propose a fast adversarial training algorithm (C-AdvUL) composed of two losses. C-AdvIPO is an adversarial variant of IPO that does not require utility data for adversarially robust alignment.
  arXiv  Detail & Related papers  (2024-05-24T14:20:09Z)
• Advancing the Robustness of Large Language Models through Self-Denoised Smoothing [50.54276872204319]
  Large language models (LLMs) have achieved significant success, but their vulnerability to adversarial perturbations has raised considerable concerns. We propose to leverage the multitasking nature of LLMs to first denoise the noisy inputs and then to make predictions based on these denoised versions. Unlike previous denoised smoothing techniques in computer vision, which require training a separate model to enhance the robustness of LLMs, our method offers significantly better efficiency and flexibility.
  arXiv  Detail & Related papers  (2024-04-18T15:47:00Z)
• Token-Level Adversarial Prompt Detection Based on Perplexity Measures and Contextual Information [67.78183175605761]
  Large Language Models are susceptible to adversarial prompt attacks. This vulnerability underscores a significant concern regarding the robustness and reliability of LLMs. We introduce a novel approach to detecting adversarial prompts at a token level.
  arXiv  Detail & Related papers  (2023-11-20T03:17:21Z)
• SatLM: Satisfiability-Aided Language Models Using Declarative Prompting [68.40726892904286]
  We propose a new satisfiability-aided language modeling (SatLM) approach for improving the reasoning capabilities of large language models (LLMs) We use an LLM to generate a declarative task specification rather than an imperative program and leverage an off-the-shelf automated theorem prover to derive the final answer. We evaluate SATLM on 8 different datasets and show that it consistently outperforms program-aided LMs in the imperative paradigm.
  arXiv  Detail & Related papers  (2023-05-16T17:55:51Z)

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.