Exploring Cross-Stage Adversarial Transferability in Class-Incremental Continual Learning

• URL: http://arxiv.org/abs/2508.08920v1
• Date: Tue, 12 Aug 2025 13:17:21 GMT
• Title: Exploring Cross-Stage Adversarial Transferability in Class-Incremental Continual Learning
• Authors: Jungwoo Kim, Jong-Seok Lee,
• Abstract summary: Class-incremental continual learning addresses catastrophic forgetting by enabling classification models to preserve knowledge of previously learned classes while acquiring new ones.<n>We present the first exploration of vulnerability to stage-transferred attacks, i.e., an adversarial example generated using the model in an earlier stage is used to attack the model in a later stage.<n>Our findings reveal that continual learning methods are highly susceptible to these attacks, raising a serious security issue.
• Score: 17.739979156009696
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Class-incremental continual learning addresses catastrophic forgetting by enabling classification models to preserve knowledge of previously learned classes while acquiring new ones. However, the vulnerability of the models against adversarial attacks during this process has not been investigated sufficiently. In this paper, we present the first exploration of vulnerability to stage-transferred attacks, i.e., an adversarial example generated using the model in an earlier stage is used to attack the model in a later stage. Our findings reveal that continual learning methods are highly susceptible to these attacks, raising a serious security issue. We explain this phenomenon through model similarity between stages and gradual robustness degradation. Additionally, we find that existing adversarial training-based defense methods are not sufficiently effective to stage-transferred attacks. Codes are available at https://github.com/mcml-official/CSAT.

Related papers

• Preliminary Investigation into Uncertainty-Aware Attack Stage Classification [81.28215542218724]
  This work addresses the problem of attack stage inference under uncertainty.<n>We propose a classification approach based on Evidential Deep Learning (EDL), which models predictive uncertainty by outputting parameters of a Dirichlet distribution over possible stages.<n>Preliminary experiments in a simulated environment demonstrate that the proposed model can accurately infer the stage of an attack with confidence.
  arXiv  Detail & Related papers  (2025-08-01T06:58:00Z)
• When Forgetting Triggers Backdoors: A Clean Unlearning Attack [1.8434042562191815]
  We propose a novel em clean backdoor attack that exploits both the model learning phase and the subsequent unlearning requests.<n>This strategy results in a powerful and stealthy novel attack that is hard to detect or mitigate.
  arXiv  Detail & Related papers  (2025-06-14T14:31:51Z)
• Sustainable Self-evolution Adversarial Training [51.25767996364584]
  We propose a Sustainable Self-Evolution Adversarial Training (SSEAT) framework for adversarial training defense models.<n>We introduce a continual adversarial defense pipeline to realize learning from various kinds of adversarial examples.<n>We also propose an adversarial data replay module to better select more diverse and key relearning data.
  arXiv  Detail & Related papers  (2024-12-03T08:41:11Z)
• Time-Aware Face Anti-Spoofing with Rotation Invariant Local Binary Patterns and Deep Learning [50.79277723970418]
  imitation attacks can lead to erroneous identification and subsequent authentication of attackers. Similar to face recognition, imitation attacks can also be detected with Machine Learning. We propose a novel approach that promises high classification accuracy by combining previously unused features with time-aware deep learning strategies.
  arXiv  Detail & Related papers  (2024-08-27T07:26:10Z)
• Model-agnostic clean-label backdoor mitigation in cybersecurity environments [6.857489153636145]
  Recent research has surfaced a series of insidious training-time attacks that inject backdoors in models designed for security classification tasks.<n>We propose new techniques that leverage insights in cybersecurity threat models to effectively mitigate these clean-label poisoning attacks.
  arXiv  Detail & Related papers  (2024-07-11T03:25:40Z)
• 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)
• A Dual-Tier Adaptive One-Class Classification IDS for Emerging Cyberthreats [3.560574387648533]
  We propose a one-class classification-driven IDS system structured on two tiers. The first tier distinguishes between normal activities and attacks/threats, while the second tier determines if the detected attack is known or unknown. This model not only identifies unseen attacks but also uses them for retraining them by clustering unseen attacks.
  arXiv  Detail & Related papers  (2024-03-17T12:26:30Z)
• usfAD Based Effective Unknown Attack Detection Focused IDS Framework [3.560574387648533]
  Internet of Things (IoT) and Industrial Internet of Things (IIoT) have led to an increasing range of cyber threats. For more than a decade, researchers have delved into supervised machine learning techniques to develop Intrusion Detection System (IDS) IDS trained and tested on known datasets fails in detecting zero-day or unknown attacks. We propose two strategies for semi-supervised learning based IDS where training samples of attacks are not required.
  arXiv  Detail & Related papers  (2024-03-17T11:49:57Z)
• 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)
• Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack [53.032801921915436]
  Human Activity Recognition (HAR) has been employed in a wide range of applications, e.g. self-driving cars. Recently, the robustness of skeleton-based HAR methods have been questioned due to their vulnerability to adversarial attacks. We show such threats exist, even when the attacker only has access to the input/output of the model. We propose the very first black-box adversarial attack approach in skeleton-based HAR called BASAR.
  arXiv  Detail & Related papers  (2022-11-21T09:51:28Z)
• Learning to Learn Transferable Attack [77.67399621530052]
  Transfer adversarial attack is a non-trivial black-box adversarial attack that aims to craft adversarial perturbations on the surrogate model and then apply such perturbations to the victim model. We propose a Learning to Learn Transferable Attack (LLTA) method, which makes the adversarial perturbations more generalized via learning from both data and model augmentation. Empirical results on the widely-used dataset demonstrate the effectiveness of our attack method with a 12.85% higher success rate of transfer attack compared with the state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-12-10T07:24:21Z)
• Temporal Sparse Adversarial Attack on Sequence-based Gait Recognition [56.844587127848854]
  We demonstrate that the state-of-the-art gait recognition model is vulnerable to such attacks. We employ a generative adversarial network based architecture to semantically generate adversarial high-quality gait silhouettes or video frames. The experimental results show that if only one-fortieth of the frames are attacked, the accuracy of the target model drops dramatically.
  arXiv  Detail & Related papers  (2020-02-22T10:08:42Z)

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.