Assessing and Improving DNN Robustness against Adversarial Examples from the Perspective of Fully Connected Layers

View at publisher Summarise with VIRAT
Authors: Ziming Zhao, Zhaoxuan Li, Tingting Li, Fan Zhang
Cited by: 0
References: 73

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Recent studies show that deep neural networks are extremely vulnerable, especially for adversarial examples of image classification models. However, existing defenses suffer from limited adaptability across attacks, an unfavorable tradeoff between clean accuracy and robustness, and substantial training-time overhead. To tackle these problems, we present a novel component, named the redundant fully connected layer, which can be combined with existing model backbones in a pluggable manner. Specifically, we design a tailor-made loss function for it that leverages cosine similarity to maximize the difference and diversity of multiple fully connected parts. We conduct extensive experiments against 12 representative attacks (white-box and black-box), based on two popular datasets. The empirical evaluations show that our scheme realizes significant outcomes against various attacks with negligible additional training overhead, while hardly bringing collateral damage for clean-instance accuracy.

Fields of Study & Subjects

Adversarial Robustness in Machine Learning Digital Media Forensic Detection Advanced Neural Network Applications

Publication details

Journal / source
IEEE Transactions on Information Forensics and Security
Pages
1–1
Publication date
1 January 2026
Language
EN