Time series classification (TSC) has emerged as a critical task in various domains, and deep neural networks(DNN) have shown superior performance in TSC tasks. However, these models are vulnerable to adversarial attacks, where subtle perturbations can significantly impact the prediction results. Existing adversarial methods often suffer from over-parameterization or random logit perturbation, hindering their effectiveness. Additionally, increasing the attack success rate (ASR) typically involves generating more noise, making the attack more easily detectable. To address these limitations, we propose SWAP, a novel attacking method for TSC models. SWAP focuses on enhancing the confidence of the second-ranked logits while minimizing the manipulation of other logits. This is achieved by minimizing the KL-divergence between the target logit distribution and the predictive logit distribution. Experimental results demonstrate that SWAP achieves state-of-the-art performance, with an ASR exceeding 50 % and an 18 % increase compared to existing methods.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    SWAP: Exploiting Second-Ranked Logits for Adversarial Attacks on Time Series


    Beteiligte:
    Dong, Chang George (Autor:in) / Zheng, Liangwei Nathan (Autor:in) / Chen, Weitong (Autor:in) / Zhang, Wei Emma (Autor:in) / Yue, Lin (Autor:in)


    Erscheinungsdatum :

    01.12.2023


    Format / Umfang :

    987294 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Exploiting Features and Logits in Heterogeneous Federated Learning

    Chan, Yun-Hin / Ngai, Edith C. -H. | ArXiv | 2022

    Freier Zugriff

    Constraining Logits by Bounded Function for Adversarial Robustness

    Kanai, Sekitoshi / Yamada, Masanori / Yamaguchi, Shin'ya et al. | ArXiv | 2020

    Freier Zugriff

    Knowledge Distillation with Refined Logits

    Sun, Wujie / Chen, Defang / Lyu, Siwei et al. | ArXiv | 2024

    Freier Zugriff

    NormKD: Normalized Logits for Knowledge Distillation

    Chi, Zhihao / Zheng, Tu / Li, Hengjia et al. | ArXiv | 2023

    Freier Zugriff

    Logits DeConfusion with CLIP for Few-Shot Learning

    Li, Shuo / Liu, Fang / Hao, Zehua et al. | ArXiv | 2025

    Freier Zugriff