Robust Dynamic Expansion for Continual Learning under Backdoor Attacks via Purification and Selective Recovery

• URL: http://arxiv.org/abs/2609.06346v1
• Date: Sun, 06 Sep 2026 02:52:44 GMT
• Title: Robust Dynamic Expansion for Continual Learning under Backdoor Attacks via Purification and Selective Recovery
• Abstract summary: In practical scenarios, task streams collected from untrusted sources may contain backdoor-poisoned samples.<n>We propose a robust dynamic-expansion framework that integrates sample purification, selective recovery, and robust expert routing.
• Score: 21.762207770794916
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continual learning (CL) enables models to acquire new knowledge from sequentially arriving tasks while retaining previously learned knowledge. However, in practical scenarios, task streams collected from untrusted sources may contain backdoor-poisoned samples, posing a critical challenge to the stability, plasticity, and security of continual learners. In this work, we investigate a challenging setting termed Continual Learning Under Backdoor Attack (CLUBA), where each incremental task may involve a small proportion of maliciously manipulated training samples. Unlike conventional continual learning or backdoor defense scenarios, CLUBA requires models to simultaneously mitigate catastrophic forgetting, preserve adaptation capability, and prevent the absorption of malicious supervision during sequential updates. To address this challenge, we propose a robust dynamic-expansion framework that integrates sample purification, selective recovery, and robust expert routing into a unified continual learning paradigm. Specifically, we introduce Bi-Prototype Purification (BPP) to identify suspicious samples by exploiting semantic discrepancies in feature space. Based on purified data, Gradient Discrepancy-based Robustness Optimization (GDBRO) selectively recovers informative poisoned samples through pseudo-label correction and gradient consistency evaluation, improving robustness while maintaining model plasticity. Furthermore, Robust Feature Consistency-based Expert Selection (RFCBES) constructs perturbation-aware class prototypes to enable reliable expert routing under corrupted or shifted inputs.

Related papers

• Understanding and Stabilizing Deep Q-Learning via Controlled Bootstrapping and Regulated Value Dynamics [2.358468106592515]
  We provide a systematic analysis of instability in deep Q-learning from three complementary perspectives.<n>We identify a reward-triggered self-reinforcing trap and characteristic parameter spike dynamics.<n>Experiments on Atari-100K and Procgen demonstrate competitive performance and improved training stability.
  arXiv  Detail & Related papers  (2026-08-17T06:55:41Z)
• ARES: Scalable and Practical Gradient Inversion Attack in Federated Learning through Activation Recovery [73.8181449261685]
  Federated Learning (FL) enables collaborative model training by sharing model updates instead of raw data, aiming to protect user privacy.<n>Recent studies reveal that these shared updates can inadvertently leak sensitive training data through gradient inversion attacks (GIAs)
  arXiv  Detail & Related papers  (2026-03-18T11:40:44Z)
• Beyond Retention: Orchestrating Structural Safety and Plasticity in Continual Learning for LLMs [2.5202137607634407]
  Experience Replay (ER) is a standard countermeasure against catastrophic forgetting.<n>ER causes negative transfer on fragile, structured domains like code generation.<n>We proposeOrthogonal Subspace Wake-up (OSW) as a mathematically grounded "safety guarantee" for established knowledge structures.
  arXiv  Detail & Related papers  (2026-01-26T08:28:02Z)
• From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models [77.04403907729738]
  This survey charts the evolution of uncertainty from a passive diagnostic metric to an active control signal guiding real-time model behavior.<n>We demonstrate how uncertainty is leveraged as an active control signal across three frontiers.<n>This survey argues that mastering the new trend of uncertainty is essential for building the next generation of scalable, reliable, and trustworthy AI.
  arXiv  Detail & Related papers  (2026-01-22T06:21:31Z)
• 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)
• DUP: Detection-guided Unlearning for Backdoor Purification in Language Models [6.726081307488787]
  DUP (Detection-guided Unlearning for Purification) is a framework that integrates backdoor detection with unlearning-based purification.<n>Based on the detection results, we purify the model through a parameter-efficient unlearning mechanism.<n>Our code is available at https://github.com/ManHu2025/DUP.
  arXiv  Detail & Related papers  (2025-08-03T08:12:21Z)
• Reshaping the Online Data Buffering and Organizing Mechanism for Continual Test-Time Adaptation [49.53202761595912]
  Continual Test-Time Adaptation involves adapting a pre-trained source model to continually changing unsupervised target domains. We analyze the challenges of this task: online environment, unsupervised nature, and the risks of error accumulation and catastrophic forgetting. We propose an uncertainty-aware buffering approach to identify and aggregate significant samples with high certainty from the unsupervised, single-pass data stream.
  arXiv  Detail & Related papers  (2024-07-12T15:48:40Z)
• 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)
• Selective Learning: Towards Robust Calibration with Dynamic Regularization [79.92633587914659]
  Miscalibration in deep learning refers to there is a discrepancy between the predicted confidence and performance. We introduce Dynamic Regularization (DReg) which aims to learn what should be learned during training thereby circumventing the confidence adjusting trade-off.
  arXiv  Detail & Related papers  (2024-02-13T11:25:20Z)
• Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization [51.34904967046097]
  Continual learning seeks to overcome the challenge of catastrophic forgetting, where a model forgets previously learnt information. We introduce a novel prior-based method that better constrains parameter growth, reducing catastrophic forgetting. Results show that BAdam achieves state-of-the-art performance for prior-based methods on challenging single-headed class-incremental experiments.
  arXiv  Detail & Related papers  (2023-09-15T17:10:51Z)
• Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior [51.60683890503293]
  We propose a theoretical framework for studying behavior cloning of complex expert demonstrations using generative modeling. We show that pure supervised cloning can generate trajectories matching the per-time step distribution of arbitrary expert trajectories.
  arXiv  Detail & Related papers  (2023-07-27T04:27:26Z)

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.