Improving Hierarchical Adversarial Robustness of Deep Neural Networks
Do all adversarial examples have the same consequences? An autonomous driving system misclassifying a pedestrian as a car may induce a far more dangerous -- and even potentially lethal -- behavior than, for instance, a car as a bus. In order to better tackle this important problematic, we introduce the concept of hierarchical adversarial robustness. Given a dataset whose classes can be grouped into coarse-level labels, we define hierarchical adversarial examples as the ones leading to a misclassification at the coarse level. To improve the resistance of neural networks to hierarchical attacks, we introduce a hierarchical adversarially robust (HAR) network design that decomposes a single classification task into one coarse and multiple fine classification tasks, before being specifically trained by adversarial defense techniques. As an alternative to an end-to-end learning approach, we show that HAR significantly improves the robustness of the network against $\ell_2$ and $\ell_{\infty}$ bounded hierarchical attacks on the CIFAR-10 and CIFAR-100 dataset.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial DefenseAdversarial RobustnessAutonomous DrivingGeneral ClassificationSimilar Papers 제목 키워드 기반
A Hierarchical Assessment of Adversarial Severity
Adversarial Robustness is a growing field that evidences the brittleness of neural networks. Although the literature on adversarial robustness is vast, a dimension is missing in these studies: assessing how severe the mi…
Adversarial RobustnessHierarchically Robust Zero-shot Vision-language Models
Vision-Language Models (VLMs) can perform zero-shot classification but are susceptible to adversarial attacks. While robust fine-tuning improves their robustness, existing approaches align fixed text embeddings with an i…
Adversarial RobustnessTowards Adversarial Robustness of Bayesian Neural Network through Hierarchical Variational Inference
Recent works have applied Bayesian Neural Network (BNN) to adversarial training, and shown the improvement of adversarial robustness via the BNN's strength of stochastic gradient defense. However, we have found that in g…
Adversarial DefenseAdversarial RobustnessBayesian InferenceProbabilistic Deep Learning+1Hierarchical Self-Supervised Adversarial Training for Robust Vision Models in Histopathology
Adversarial attacks pose significant challenges for vision models in critical fields like healthcare, where reliability is essential. Although adversarial training has been well studied in natural images, its application…
Contrastive LearningHierarchical Distribution-Aware Testing of Deep Learning
Deep Learning (DL) is increasingly used in safety-critical applications, raising concerns about its reliability. DL suffers from a well-known problem of lacking robustness, especially when faced with adversarial perturba…
Adversarial RobustnessData CompressionDeep Learning