Exploring Misclassifications of Robust Neural Networks to Enhance Adversarial Attacks

2021-05-21 · Leo Schwinn, René Raab, An Nguyen, Dario Zanca, Bjoern Eskofier

Progress in making neural networks more robust against adversarial attacks is mostly marginal, despite the great efforts of the research community. Moreover, the robustness evaluation is often imprecise, making it difficult to identify promising approaches. We analyze the classification decisions of 19 different state-of-the-art neural networks trained to be robust against adversarial attacks. Our findings suggest that current untargeted adversarial attacks induce misclassification towards only a limited amount of different classes. Additionally, we observe that both over- and under-confidence in model predictions result in an inaccurate assessment of model robustness. Based on these observations, we propose a novel loss function for adversarial attacks that consistently improves attack success rate compared to prior loss functions for 19 out of 19 analyzed models.

📄 PDF Abstract BibTeX arXiv:2105.10304

Code (0)

등록된 구현이 없습니다.

Adversarial Evasion Attacks on Computer Vision using SHAP Values

2026-01-15 · Frank Mollard, Marcus Becker, Florian Roehrbein arxiv

The paper introduces a white-box attack on computer vision models using SHAP values. It demonstrates how adversarial evasion attacks can compromise the performance of deep learning models by reducing output confidence or…

Adaptive Meta-learning-based Adversarial Training for Robust Automatic Modulation Classification

2025-01-03 · Amirmohammad Bamdad, Ali Owfi, Fatemeh Afghah

DL-based automatic modulation classification (AMC) models are highly susceptible to adversarial attacks, where even minimal input perturbations can cause severe misclassifications. While adversarially training an AMC mod…

Adversarial Attack Meta-Learning

End-to-End Adversarial White Box Attacks on Music Instrument Classification

2020-07-29 · Katharina Prinz, Arthur Flexer

Small adversarial perturbations of input data are able to drastically change performance of machine learning systems, thereby challenging the validity of such systems. We present the very first end-to-end adversarial att…

BIG-bench Machine Learning General Classification

Enhancing Adversarial Robustness of Deep Neural Networks Through Supervised Contrastive Learning

2024-12-27 · Longwei Wang, Navid Nayyem, Abdullah Rakin

Adversarial attacks exploit the vulnerabilities of convolutional neural networks by introducing imperceptible perturbations that lead to misclassifications, exposing weaknesses in feature representations and decision bou…

Adversarial Robustness Contrastive Learning

AdvIRL: Reinforcement Learning-Based Adversarial Attacks on 3D NeRF Models

2024-12-18 · Tommy Nguyen, Mehmet Ergezer, Christian Green

The increasing deployment of AI models in critical applications has exposed them to significant risks from adversarial attacks. While adversarial vulnerabilities in 2D vision models have been extensively studied, the thr…

CPU NeRF