Don't Break the Boundary: Continual Unlearning for OOD Detection Based on Free Energy Repulsion

• URL: http://arxiv.org/abs/2602.06331v1
• Date: Fri, 06 Feb 2026 02:55:47 GMT
• Title: Don't Break the Boundary: Continual Unlearning for OOD Detection Based on Free Energy Repulsion
• Abstract summary: Out-of-Distribution (OOD) detection is essential for trustworthy AI in open-world environments.<n>Traditional unlearning methods disrupt this delicate structure, leading to a catastrophic loss of the model's capability to discriminate anomalies.<n>We propose TFER, which anchors retained classes within a low-energy ID manifold through a pull mechanism, while actively expelling forgotten classes to high-energy OOD regions.
• Score: 8.714183507567087
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deploying trustworthy AI in open-world environments faces a dual challenge: the necessity for robust Out-of-Distribution (OOD) detection to ensure system safety, and the demand for flexible machine unlearning to satisfy privacy compliance and model rectification. However, this objective encounters a fundamental geometric contradiction: current OOD detectors rely on a static and compact data manifold, whereas traditional classification-oriented unlearning methods disrupt this delicate structure, leading to a catastrophic loss of the model's capability to discriminate anomalies while erasing target classes. To resolve this dilemma, we first define the problem of boundary-preserving class unlearning and propose a pivotal conceptual shift: in the context of OOD detection, effective unlearning is mathematically equivalent to transforming the target class into OOD samples. Based on this, we propose the TFER (Total Free Energy Repulsion) framework. Inspired by the free energy principle, TFER constructs a novel Push-Pull game mechanism: it anchors retained classes within a low-energy ID manifold through a pull mechanism, while actively expelling forgotten classes to high-energy OOD regions using a free energy repulsion force. This approach is implemented via parameter-efficient fine-tuning, circumventing the prohibitive cost of full retraining. Extensive experiments demonstrate that TFER achieves precise unlearning while maximally preserving the model's discriminative performance on remaining classes and external OOD data. More importantly, our study reveals that the unique Push-Pull equilibrium of TFER endows the model with inherent structural stability, allowing it to effectively resist catastrophic forgetting without complex additional constraints, thereby demonstrating exceptional potential in continual unlearning tasks.

Related papers

• Towards a Resilience-Theoretic Foundation for Adversarial Robustness in Industrial Control System Anomaly Detection [0.0]
  Anomaly-based intrusion detection systems in industrial control systems (ICS) and operational technology (OT) environments are increasingly required to meet formal resilience criteria.<n>Existing resilience frameworks for cyber-physical systems define absorb-recover-adapt trajectories at the architectural level but do not treat machine learning anomaly detectors as first-class components.<n>In this paper, we establish that adversarial robustness in ICS anomaly detection is a specific instantiation of system resilience.
  arXiv  Detail & Related papers  (2026-09-07T09:04:30Z)
• On-the-go Forgetting without Explicit Unlearning via ERASE [2.6426981014417046]
  ERASE is a framework for on-the-go forgetting that suppresses the observable influence of private data without modifying model weights.<n>We rigorously characterize sufficient conditions when ERASE provably achieves functional forgetting of designated subclasses.<n> ERASE maintains the best observed balance between forgetting efficacy, computational efficiency, and retention fidelity over recent unlearning-based methods.
  arXiv  Detail & Related papers  (2026-09-05T08:09:27Z)
• Energy-Structured Low-Rank Adaptation for Continual Learning [78.5390284258307]
  We propose textbfEnergy-Concentrated and textbfEnergy-Ordered textbfLow-textbfRank textbfAdaptation (E$2$-LoRA)<n>By explicitly ordering and concentrating knowledge into leading ranks, E$2$-LoRA frees capacity for subsequent tasks.
  arXiv  Detail & Related papers  (2026-05-26T12:55:02Z)
• HamBR: Active Decision Boundary Restoration Based on Hamiltonian Dynamics for Learning with Noisy Labels [5.589730766225291]
  In large-scale visual recognition and data mining tasks, the presence of noisy labels severely undermines the generalization capability of deep neural networks (DNNs)<n>This study is the first to emphasize the pivotal importance of active boundary restoration for noise-robust learning.<n>We propose HamBR, a novel paradigm based on Hamiltonian dynamics.
  arXiv  Detail & Related papers  (2026-05-12T01:14:35Z)
• Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling [49.41422138354821]
  We propose a principled reward modeling framework that integrates non-negative factor analysis into the Bradley-Terry preference model.<n>BNRM represents rewards through a sparse, non-negative latent factor generative process.<n>We show that BNRM substantially mitigates reward over-optimization, improves robustness under distribution shifts, and yields more interpretable reward decompositions than strong baselines.
  arXiv  Detail & Related papers  (2026-02-11T08:14:11Z)
• Representation-Aware Unlearning via Activation Signatures: From Suppression to Knowledge-Signature Erasure [2.0017902634527194]
  We introduce Knowledge Immunization Framework (KIF), a representation-aware architecture that distinguishes genuine erasure from obfuscation.<n>Our approach combines dynamic suppression of subject-specific representations with parameter-efficient adaptation, enabling durable unlearning without full model retraining.
  arXiv  Detail & Related papers  (2026-01-15T16:28:14Z)
• LEGATO: Good Identity Unlearning Is Continuous [30.78585550012454]
  LEGATO is a machine unlearning method for learning to forget identity of generative models.<n>It achieves state-of-the-art forgetting performance, avoids catastrophic collapse and reduces fine-tuned parameters.<n>Our experiments show that LEGATO achieves state-of-the-art forgetting performance, avoids catastrophic collapse and reduces fine-tuned parameters.
  arXiv  Detail & Related papers  (2026-01-07T13:15:25Z)
• Relative Energy Learning for LiDAR Out-of-Distribution Detection [2.9740664660400804]
  Out-of-distribution (OOD) detection is a critical requirement for reliable autonomous driving.<n>We propose Relative Energy Learning (REL), a framework for OOD detection in LiDAR point clouds.<n>To address the absence of OOD samples during training, we propose a lightweight data synthesis strategy called Point Raise.
  arXiv  Detail & Related papers  (2025-11-10T05:29:18Z)
• Towards Robust Artificial Intelligence: Self-Supervised Learning Approach for Out-of-Distribution Detection [0.19599274203282294]
  This paper proposes an approach to improve OOD detection without the need of labeled data.<n>The proposed approach leverages the principles of self-supervised learning, allowing the model to learn useful representations from unlabeled data.
  arXiv  Detail & Related papers  (2025-10-14T16:55:25Z)
• ERIS: An Energy-Guided Feature Disentanglement Framework for Out-of-Distribution Time Series Classification [51.07970070817353]
  An ideal time series classification (TSC) should be able to capture invariant representations.<n>Current methods are largely unguided, lacking the semantic direction required to isolate truly universal features.<n>We propose an end-to-end Energy-Regularized Information for Shift-Robustness framework to enable guided and reliable feature disentanglement.
  arXiv  Detail & Related papers  (2025-08-19T12:13:41Z)
• MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models [56.09354775405601]
  Model extraction attacks aim to replicate the functionality of a black-box model through query access.<n>Most existing defenses presume that attacker queries have out-of-distribution (OOD) samples, enabling them to detect and disrupt suspicious inputs.<n>We propose MISLEADER, a novel defense strategy that does not rely on OOD assumptions.
  arXiv  Detail & Related papers  (2025-06-03T01:37:09Z)
• HUWSOD: Holistic Self-training for Unified Weakly Supervised Object Detection [66.42229859018775]
  We introduce a unified, high-capacity weakly supervised object detection (WSOD) network called HUWSOD. HUWSOD incorporates a self-supervised proposal generator and an autoencoder proposal generator with a multi-rate re-supervised pyramid to replace traditional object proposals. Our findings indicate that randomly boxes, although significantly different from well-designed offline object proposals, are effective for WSOD training.
  arXiv  Detail & Related papers  (2024-06-27T17:59:49Z)
• A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Training [64.71254710803368]
  Adversarial Training (AT) is an effective approach to enhance the robustness of deep neural networks. We demystify this phenomenon by developing a unified probabilistic framework, called Contrastive Energy-based Models (CEM) We propose a principled method to develop adversarial learning and sampling methods.
  arXiv  Detail & Related papers  (2022-03-25T05:33:34Z)
• Weakly Supervised Semantic Segmentation via Alternative Self-Dual Teaching [82.71578668091914]
  This paper establishes a compact learning framework that embeds the classification and mask-refinement components into a unified deep model. We propose a novel alternative self-dual teaching (ASDT) mechanism to encourage high-quality knowledge interaction.
  arXiv  Detail & Related papers  (2021-12-17T11:56:56Z)
• Policy Smoothing for Provably Robust Reinforcement Learning [109.90239627115336]
  We study the provable robustness of reinforcement learning against norm-bounded adversarial perturbations of the inputs. We generate certificates that guarantee that the total reward obtained by the smoothed policy will not fall below a certain threshold under a norm-bounded adversarial of perturbation the input.
  arXiv  Detail & Related papers  (2021-06-21T21:42:08Z)

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.