Adversarial Defense by Suppressing High-frequency Components
Recent works show that deep neural networks trained on image classification dataset bias towards textures. Those models are easily fooled by applying small high-frequency perturbations to clean images. In this paper, we learn robust image classification models by removing high-frequency components. Specifically, we develop a differentiable high-frequency suppression module based on discrete Fourier transform (DFT). Combining with adversarial training, we won the 5th place in the IJCAI-2019 Alibaba Adversarial AI Challenge. Our code is available online.
Code (1)
Tasks
Adversarial DefenseClassificationGeneral Classificationimage-classificationImage ClassificationVocal Bursts Intensity PredictionSimilar Papers 제목 키워드 기반
LPF-Defense: 3D Adversarial Defense based on Frequency Analysis
Although 3D point cloud classification has recently been widely deployed in different application scenarios, it is still very vulnerable to adversarial attacks. This increases the importance of robust training of 3D mode…
3D Point Cloud ClassificationAdversarial DefensePoint Cloud ClassificationExploring Frequencies via Feature Mixing and Meta-Learning for Improving Adversarial Transferability
Recent studies have shown that Deep Neural Networks (DNNs) are susceptible to adversarial attacks, with frequency-domain analysis underscoring the significance of high-frequency components in influencing model prediction…
Meta-LearningA Frequency Perspective of Adversarial Robustness
Adversarial examples pose a unique challenge for deep learning systems. Despite recent advances in both attacks and defenses, there is still a lack of clarity and consensus in the community about the true nature and unde…
Adversarial RobustnessToward Few-step Adversarial Training from a Frequency Perspective
We investigate adversarial-sample generation methods from a frequency domain perspective and extend standard $l_{\infty}$ Projected Gradient Descent (PGD) to the frequency domain. The resulting method, which we call Spec…
On the Effectiveness of Low Frequency Perturbations
Carefully crafted, often imperceptible, adversarial perturbations have been shown to cause state-of-the-art models to yield extremely inaccurate outputs, rendering them unsuitable for safety-critical application domains.…
Adversarial AttackAdversarial Robustness