Improving LLM Unlearning Robustness via Random Perturbations

• URL: http://arxiv.org/abs/2501.19202v3
• Date: Mon, 19 May 2025 20:41:58 GMT
• Title: Improving LLM Unlearning Robustness via Random Perturbations
• Authors: Dang Huu-Tien, Hoang Thanh-Tung, Anh Bui, Le-Minh Nguyen, Naoya Inoue,
• Abstract summary: We show that current state-of-the-art LLM unlearning methods inherently reduce models' robustness, causing them to misbehave even when a single non-adversarial forget-token is in the retain-query.<n>To mitigate this vulnerability, we propose Random Noise Augmentation (RNA) -- a plug-and-play, model and method agnostic approach with theoretical guarantees for improving the robustness of unlearned models.
• Score: 6.287449249401005
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we show that current state-of-the-art LLM unlearning methods inherently reduce models' robustness, causing them to misbehave even when a single non-adversarial forget-token is in the retain-query. Toward understanding underlying causes, we reframe the unlearning process as backdoor attacks and defenses: forget-tokens act as backdoor triggers that, when activated in retain-queries, cause disruptions in unlearned models' behaviors, similar to successful backdoor attacks. To mitigate this vulnerability, we propose Random Noise Augmentation (RNA) -- a plug-and-play, model and method agnostic approach with theoretical guarantees for improving the robustness of unlearned models. Extensive experiments demonstrate that RNA significantly improves the robustness of unlearned models, maintains unlearning performances while introducing no additional computational overhead.

Related papers

• Robust Anti-Backdoor Instruction Tuning in LVLMs [53.766434746801366]
  We introduce a lightweight, certified-agnostic defense framework for large visual language models (LVLMs)<n>Our framework finetunes only adapter modules and text embedding layers under instruction tuning.<n>Experiments against seven attacks on Flickr30k and MSCOCO demonstrate that ours reduces their attack success rate to nearly zero.
  arXiv  Detail & Related papers  (2025-06-04T01:23:35Z)
• Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy [36.19634262653306]
  This paper reveals a critical vulnerability in fine-tuning-based unlearning.<n>A malicious user can craft a manipulated forgetting request that stealthily degrades the model's utility for benign users.<n>We propose Scope-aware Unlearning (SU), a lightweight enhancement that introduces a scope term into the unlearning objective.
  arXiv  Detail & Related papers  (2025-05-31T02:57:24Z)
• Adversarial Training of Reward Models [74.17196154247964]
  We introduce Adv-RM, a novel adversarial training framework that automatically identifies adversarial examples. By leveraging reinforcement learning, Adv-RM trains a policy to expose vulnerabilities in large state-of-the-art reward models. We demonstrate that Adv-RM significantly outperforms conventional reward training.
  arXiv  Detail & Related papers  (2025-04-08T15:38:25Z)
• A generative approach to LLM harmfulness detection with special red flag tokens [15.796683630119654]
  We propose to expand the model's vocabulary with a special token we call red flag token (rf>) This novel safety training method effectively augments LLMs into generative classifiers of harmfulness at all times during the conversation. It also evaluates each generated answer rather than just the input prompt and provides a stronger defence against sampling-based attacks.
  arXiv  Detail & Related papers  (2025-02-22T21:48:48Z)
• REFINE: Inversion-Free Backdoor Defense via Model Reprogramming [60.554146386198376]
  Backdoor attacks on deep neural networks (DNNs) have emerged as a significant security threat. We propose REFINE, an inversion-free backdoor defense method based on model reprogramming.
  arXiv  Detail & Related papers  (2025-02-22T07:29:12Z)
• Defensive Dual Masking for Robust Adversarial Defense [5.932787778915417]
  This paper introduces the Defensive Dual Masking (DDM) algorithm, a novel approach designed to enhance model robustness against such attacks.<n>DDM utilizes a unique adversarial training strategy where [MASK] tokens are strategically inserted into training samples to prepare the model to handle adversarial perturbations more effectively.<n>During inference, potentially adversarial tokens are dynamically replaced with [MASK] tokens to neutralize potential threats while preserving the core semantics of the input.
  arXiv  Detail & Related papers  (2024-12-10T00:41:25Z)
• Transferable Adversarial Attacks on SAM and Its Downstream Models [87.23908485521439]
  This paper explores the feasibility of adversarial attacking various downstream models fine-tuned from the segment anything model (SAM) To enhance the effectiveness of the adversarial attack towards models fine-tuned on unknown datasets, we propose a universal meta-initialization (UMI) algorithm.
  arXiv  Detail & Related papers  (2024-10-26T15:04:04Z)
• Avoiding mode collapse in diffusion models fine-tuned with reinforcement learning [0.0]
  Fine-tuning foundation models via reinforcement learning (RL) has proven promising for aligning to downstream objectives. We exploit the hierarchical nature of diffusion models (DMs) and train them dynamically at each epoch with a tailored RL method. We show that models trained with HRF achieve better preservation of diversity in downstream tasks, thus enhancing the fine-tuning robustness and at uncompromising mean rewards.
  arXiv  Detail & Related papers  (2024-10-10T19:06:23Z)
• Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats [52.94388672185062]
  We propose an efficient defense mechanism against backdoor threats using a concept known as machine unlearning. This entails strategically creating a small set of poisoned samples to aid the model's rapid unlearning of backdoor vulnerabilities. In the backdoor unlearning process, we present a novel token-based portion unlearning training regime.
  arXiv  Detail & Related papers  (2024-09-29T02:55:38Z)
• Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models [19.015202590038996]
  We design Dynamic Unlearning Attack (DUA), a dynamic and automated framework to attack unlearned models. We propose Latent Adrial Unlearning (LAU), a universal framework that effectively enhances the robustness of the unlearned process. We demonstrate that LAU improves unlearning effectiveness by over $53.5%$, cause only less than a $11.6%$ reduction in neighboring knowledge, and have almost no impact on the model's general capabilities.
  arXiv  Detail & Related papers  (2024-08-20T09:36:04Z)
• BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models [57.5404308854535]
  Safety backdoor attacks in large language models (LLMs) enable the stealthy triggering of unsafe behaviors while evading detection during normal interactions. We present BEEAR, a mitigation approach leveraging the insight that backdoor triggers induce relatively uniform drifts in the model's embedding space. Our bi-level optimization method identifies universal embedding perturbations that elicit unwanted behaviors and adjusts the model parameters to reinforce safe behaviors against these perturbations.
  arXiv  Detail & Related papers  (2024-06-24T19:29:47Z)
• Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning [49.242828934501986]
  Multimodal contrastive learning has emerged as a powerful paradigm for building high-quality features. backdoor attacks subtly embed malicious behaviors within the model during training. We introduce an innovative token-based localized forgetting training regime.
  arXiv  Detail & Related papers  (2024-03-24T18:33:15Z)
• Stable Unlearnable Example: Enhancing the Robustness of Unlearnable Examples via Stable Error-Minimizing Noise [31.586389548657205]
  Unlearnable example is proposed to significantly degrade the generalization performance of models by adding a kind of imperceptible noise to the data. We introduce stable error-minimizing noise (SEM), which trains the defensive noise against random perturbation instead of the time-consuming adversarial perturbation. SEM achieves a new state-of-the-art performance on CIFAR-10, CIFAR-100, and ImageNet Subset.
  arXiv  Detail & Related papers  (2023-11-22T01:43:57Z)
• Learn from the Past: A Proxy Guided Adversarial Defense Framework with Self Distillation Regularization [53.04697800214848]
  Adversarial Training (AT) is pivotal in fortifying the robustness of deep learning models. AT methods, relying on direct iterative updates for target model's defense, frequently encounter obstacles such as unstable training and catastrophic overfitting. We present a general proxy guided defense framework, LAST' (bf Learn from the Pbf ast)
  arXiv  Detail & Related papers  (2023-10-19T13:13:41Z)
• Black-box Adversarial Attacks against Dense Retrieval Models: A Multi-view Contrastive Learning Method [115.29382166356478]
  We introduce the adversarial retrieval attack (AREA) task. It is meant to trick DR models into retrieving a target document that is outside the initial set of candidate documents retrieved by the DR model. We find that the promising results that have previously been reported on attacking NRMs, do not generalize to DR models. We propose to formalize attacks on DR models as a contrastive learning problem in a multi-view representation space.
  arXiv  Detail & Related papers  (2023-08-19T00:24:59Z)
• Beyond Pretrained Features: Noisy Image Modeling Provides Adversarial Defense [52.66971714830943]
  Masked image modeling (MIM) has made it a prevailing framework for self-supervised visual representation learning. In this paper, we investigate how this powerful self-supervised learning paradigm can provide adversarial robustness to downstream classifiers. We propose an adversarial defense method, referred to as De3, by exploiting the pretrained decoder for denoising.
  arXiv  Detail & Related papers  (2023-02-02T12:37:24Z)
• Backdoor Defense via Suppressing Model Shortcuts [91.30995749139012]
  In this paper, we explore the backdoor mechanism from the angle of the model structure. We demonstrate that the attack success rate (ASR) decreases significantly when reducing the outputs of some key skip connections.
  arXiv  Detail & Related papers  (2022-11-02T15:39:19Z)
• RelaxLoss: Defending Membership Inference Attacks without Losing Utility [68.48117818874155]
  We propose a novel training framework based on a relaxed loss with a more achievable learning target. RelaxLoss is applicable to any classification model with added benefits of easy implementation and negligible overhead. Our approach consistently outperforms state-of-the-art defense mechanisms in terms of resilience against MIAs.
  arXiv  Detail & Related papers  (2022-07-12T19:34:47Z)
• Towards Assessing and Characterizing the Semantic Robustness of Face Recognition [55.258476405537344]
  Face Recognition Models (FRMs) based on Deep Neural Networks (DNNs) inherit this vulnerability. We propose a methodology for assessing and characterizing the robustness of FRMs against semantic perturbations to their input.
  arXiv  Detail & Related papers  (2022-02-10T12:22:09Z)
• SafeAMC: Adversarial training for robust modulation recognition models [53.391095789289736]
  In communication systems, there are many tasks, like modulation recognition, which rely on Deep Neural Networks (DNNs) models. These models have been shown to be susceptible to adversarial perturbations, namely imperceptible additive noise crafted to induce misclassification. We propose to use adversarial training, which consists of fine-tuning the model with adversarial perturbations, to increase the robustness of automatic modulation recognition models.
  arXiv  Detail & Related papers  (2021-05-28T11:29:04Z)
• A Deep Marginal-Contrastive Defense against Adversarial Attacks on 1D Models [3.9962751777898955]
  Deep learning algorithms have been recently targeted by attackers due to their vulnerability. Non-continuous deep models are still not robust against adversarial attacks. We propose a novel objective/loss function, which enforces the features to lie under a specified margin to facilitate their prediction.
  arXiv  Detail & Related papers  (2020-12-08T20:51:43Z)
• RAB: Provable Robustness Against Backdoor Attacks [20.702977915926787]
  We focus on certifying the machine learning model robustness against general threat models, especially backdoor attacks. We propose the first robust training process, RAB, to smooth the trained model and certify its robustness against backdoor attacks. We conduct comprehensive experiments for different machine learning (ML) models and provide the first benchmark for certified robustness against backdoor attacks.
  arXiv  Detail & Related papers  (2020-03-19T17:05:51Z)

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.