TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting

• URL: http://arxiv.org/abs/2605.22365v2
• Date: Mon, 25 May 2026 01:50:16 GMT
• Title: TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting
• Abstract summary: Time Series Forecasting (TSF) is highly vulnerable to backdoor attacks.<n>Data entanglement induces channel-level signal dilution, rendering sample-filtering and trigger-synthesis defenses ineffective at localizing backdoors.<n>We propose a training-time backdoor defense for TSF, termed TimeGuard.
• Score: 69.01242632976161
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Time Series Forecasting (TSF) is highly vulnerable to backdoor attacks, yet effective defenses remain underexplored due to challenges arising from data entanglement and shifts in task formulation. To fill this gap, we conduct a systematic evaluation of thirteen representative backdoor defenses across the TSF life cycle and analyze their failure modes. Our results reveal two fundamental issues: (1) data entanglement induces channel-level signal dilution, rendering sample-filtering and trigger-synthesis defenses ineffective at localizing backdoors; and (2) task-formulation shift leads to training-loss degeneration, causing poisoned and clean windows to become indistinguishable at training stages. Based on these findings, we propose a training-time backdoor defense for TSF, termed TimeGuard. Our method adopts channel-wise pool training as the core paradigm and initializes a high-confidence pool using time-aware criteria to mitigate signal dilution. Moreover, we introduce distance-regularized loss selection to progressively expand the reliable pool during training and ease loss degeneration. Extensive experiments across multiple datasets, forecasting architectures, and TSF backdoor attacks demonstrate that TimeGuard substantially improves robustness, boosting $\mathrm{MAE}_\mathrm{P}$ by $1.96\times$ over the leading baseline, while preserving clean performance within 5% $\mathrm{MAE}_\mathrm{C}$.

Related papers

• Secure-CHG: A Comprehensive Framework for Robust and Fair Federated Learning via Hybrid Defense and Contribution-Aware Trust [4.5294318938213465]
  Federated Learning (FL) is highly susceptible to stealthy backdoor attacks.<n>We identify a fundamental vulnerability termed Late-stage Failure''<n>We propose Secure-CHG, a hybrid framework that pivots the defense paradigm from morphological detection toward intrinsic semantic contribution verification.
  arXiv  Detail & Related papers  (2026-06-30T02:53:16Z)
• BadTime: An Effective Backdoor Attack on Multivariate Long-Term Time Series Forecasting [7.944280447232543]
  We propose the first effective attack method named BadTime against MLTSF models.<n>BadTime executes a backdoor attack by poisoning training data and customizing the backdoor training process.<n>We show that BadTime significantly outperforms state-of-the-art (SOTA) backdoor attacks on time series forecasting.
  arXiv  Detail & Related papers  (2025-08-06T08:18:01Z)
• Coward: Toward Practical Proactive Federated Backdoor Defense via Collision-based Watermark [90.94234374893287]
  We introduce a new proactive defense, dubbed Coward, inspired by our discovery of multi-backdoor collision effects.<n>In general, we detect attackers by evaluating whether the server-injected, conflicting global watermark is erased during local training rather than retained.
  arXiv  Detail & Related papers  (2025-08-04T06:51:33Z)
• REFINE: Inversion-Free Backdoor Defense via Model Reprogramming [60.554146386198376]
  Backdoor attacks on deep neural networks (DNNs) have emerged as a significant security threat.<n>We propose REFINE, an inversion-free backdoor defense method based on model reprogramming.
  arXiv  Detail & Related papers  (2025-02-22T07:29:12Z)
• TrojanTime: Backdoor Attacks on Time Series Classification [11.17661845517885]
  Time Series Classification (TSC) is highly vulnerable to backdoor attacks.<n>We propose TrojanTime, a novel two-step training algorithm.<n>We show that TrojanTime executes backdoor attacks while maintaining clean accuracy.
  arXiv  Detail & Related papers  (2025-02-02T03:24:24Z)
• Mind the Cost of Scaffold! Benign Clients May Even Become Accomplices of Backdoor Attack [16.104941796138128]
  BadSFL is the first backdoor attack targeting Scaffold.<n>It steers benign clients' local gradient updates towards the attacker's poisoned direction, effectively turning them into unwitting accomplices.<n>BadSFL achieves superior attack durability, maintaining effectiveness for over 60 global rounds, lasting up to three times longer than existing baselines.
  arXiv  Detail & Related papers  (2024-11-25T07:46:57Z)
• 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)
• SDBA: A Stealthy and Long-Lasting Durable Backdoor Attack in Federated Learning [0.6562256987706128]
  Federated learning is a promising approach for training machine learning models while preserving data privacy.<n>This paper introduces SDBA, a novel backdoor attack mechanism designed for NLP tasks in federated learning environments.
  arXiv  Detail & Related papers  (2024-09-23T08:30:57Z)
• Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift [104.76588209308666]
  This paper explores backdoor attacks in LVLM instruction tuning across mismatched training and testing domains.<n>We introduce a new evaluation dimension, backdoor domain generalization, to assess attack robustness.<n>We propose a multimodal attribution backdoor attack (MABA) that injects domain-agnostic triggers into critical areas.
  arXiv  Detail & Related papers  (2024-06-27T02:31:03Z)
• 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)
• Backdoor Defense via Adaptively Splitting Poisoned Dataset [57.70673801469096]
  Backdoor defenses have been studied to alleviate the threat of deep neural networks (DNNs) being backdoor attacked and maliciously altered. We argue that the core of training-time defense is to select poisoned samples and to handle them properly. Under our framework, we propose an adaptively splitting dataset-based defense (ASD)
  arXiv  Detail & Related papers  (2023-03-23T02:16:38Z)
• FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning [66.56240101249803]
  We study how hardening benign clients can affect the global model (and the malicious clients) We propose a trigger reverse engineering based defense and show that our method can achieve improvement with guarantee robustness. Our results on eight competing SOTA defense methods show the empirical superiority of our method on both single-shot and continuous FL backdoor attacks.
  arXiv  Detail & Related papers  (2022-10-23T22:24:03Z)
• Towards a Defense against Backdoor Attacks in Continual Federated Learning [26.536009090970257]
  We propose a novel framework for defending against backdoor attacks in the federated continual learning setting. Our framework trains two models in parallel: a backbone model and a shadow model. We show experimentally that our framework significantly improves upon existing defenses against backdoor attacks.
  arXiv  Detail & Related papers  (2022-05-24T03:04:21Z)

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.