+

Li et al., 2025 - Google Patents

On the importance of backbone to the adversarial robustness of object detectors

Li et al., 2025

View PDF
Document ID
7077506302135002113
Author
Li X
Chen H
Hu X
Publication year
Publication venue
IEEE Transactions on Information Forensics and Security

External Links

Snippet

Object detection is a critical component of various security-sensitive applications, such as autonomous driving and video surveillance. However, existing object detectors are vulnerable to adversarial attacks, which poses a significant challenge to their reliability and …
Continue reading at arxiv.org (PDF) (other versions)

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00Network architectures or network communication protocols for network security
    • H04L63/14Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
    • H04L63/1408Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic
    • H04L63/1416Event detection, e.g. attack signature detection

Similar Documents

Publication Publication Date Title
Miller et al. Adversarial learning targeting deep neural network classification: A comprehensive review of defenses against attacks
Zhang et al. Adversarial examples: Opportunities and challenges
Wang et al. Amora: Black-box adversarial morphing attack
Wang et al. Transferable multimodal attack on vision-language pre-training models
Aldahdooh et al. Revisiting model’s uncertainty and confidences for adversarial example detection
Li et al. On the importance of backbone to the adversarial robustness of object detectors
Ye et al. Detection defense against adversarial attacks with saliency map
Zhang et al. A local perturbation generation method for GAN-generated face anti-forensics
Fan et al. Integration of statistical detector and Gaussian noise injection detector for adversarial example detection in deep neural networks
Chen et al. Defakehop++: An enhanced lightweight deepfake detector
Jia et al. Fast propagation is better: Accelerating single-step adversarial training via sampling subnetworks
Wang et al. Improving transferability of universal adversarial perturbation with feature disruption
Du et al. LC-GAN: Improving adversarial robustness of face recognition systems on edge devices
Miao et al. Spn: A method of few-shot traffic classification with out-of-distribution detection based on siamese prototypical network
Li et al. Pixel bleach network for detecting face forgery under compression
Zhao et al. Extracting cloud-based model with prior knowledge
Lu et al. Ensemble learning methods of adversarial attacks and defenses in computer vision: Recent progress
Ding et al. Zero-shot out-of-distribution detection with outlier label exposure
Wang et al. Defending adversarial attacks via semantic feature manipulation
Park et al. MalCL: Leveraging gan-based generative replay to combat catastrophic forgetting in malware classification
Song et al. Segtrans: Transferable adversarial examples for segmentation models
Bogun et al. Saliency diversified deep ensemble for robustness to adversaries
Qiang et al. An incremental malware classification approach based on few-shot learning
Huang et al. Adversarial perturbation denoising utilizing common characteristics in deep feature space
CN115984667B (en) Fisher information-based method for improving generalization capability of countermeasure training
点击 这是indexloc提供的php浏览器服务,不要输入任何密码和下载