paper-with-me

홈 › Papers

Frequency Regularization for Improving Adversarial Robustness

2022-12-24 · Binxiao Huang, Chaofan Tao, Rui Lin, Ngai Wong

Deep neural networks are incredibly vulnerable to crafted, human-imperceptible adversarial perturbations. Although adversarial training (AT) has proven to be an effective defense approach, we find that the AT-trained models heavily rely on the input low-frequency content for judgment, accounting for the low standard accuracy. To close the large gap between the standard and robust accuracies during AT, we investigate the frequency difference between clean and adversarial inputs, and propose a frequency regularization (FR) to align the output difference in the spectral domain. Besides, we find Stochastic Weight Averaging (SWA), by smoothing the kernels over epochs, further improves the robustness. Among various defense schemes, our method achieves the strongest robustness against attacks by PGD-20, C\&W and Autoattack, on a WideResNet trained on CIFAR-10 without any extra data.

📄 PDF Abstract BibTeX arXiv:2212.12732

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Robustness

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Average Pooling 설명 없음
Residual Connection 설명 없음
Batch Normalization 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Kaiming Initialization 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Wide Residual Block 설명 없음

Similar Papers 제목 키워드 기반

Wavelet Regularization Benefits Adversarial Training

2022-06-08 · Jun Yan, Huilin Yin, Xiaoyang Deng, Ziming Zhao 외

Adversarial training methods are state-of-the-art (SOTA) empirical defense methods against adversarial examples. Many regularization methods have been proven to be effective with the combination of adversarial training. …

Adversarial Robustness

Smooth Kernels Improve Adversarial Robustness and Perceptually-Aligned Gradients

2020-01-01 · ICLR 2020 1 · Haohan Wang, Xindi Wu, Songwei Ge, Zachary C. Lipton 외

Recent research has shown that CNNs are often overly sensitive to high-frequency textural patterns. Inspired by the intuition that humans are more sensitive to the lower-frequency (larger-scale) patterns we design a regu…

Adversarial Robustness

Mitigating Low-Frequency Bias: Feature Recalibration and Frequency Attention Regularization for Adversarial Robustness

2024-07-04 · Kejia Zhang, Juanjuan Weng, Yuanzheng Cai, Zhiming Luo 외

Ensuring the robustness of deep neural networks against adversarial attacks remains a fundamental challenge in computer vision. While adversarial training (AT) has emerged as a promising defense strategy, our analysis re…

Adversarial RobustnessDisentanglement

How Does Frequency Bias Affect the Robustness of Neural Image Classifiers against Common Corruption and Adversarial Perturbations?

2022-05-09 · Alvin Chan, Yew-Soon Ong, Clement Tan

Model robustness is vital for the reliable deployment of machine learning models in real-world applications. Recent studies have shown that data augmentation can result in model over-relying on features in the low-freque…

Data Augmentation

Fast Adversarial Training with Weak-to-Strong Spatial-Temporal Consistency in the Frequency Domain on Videos

2025-04-21 · Songping Wang, Hanqing Liu, Yueming Lyu, Xiantao Hu 외

Adversarial Training (AT) has been shown to significantly enhance adversarial robustness via a min-max optimization approach. However, its effectiveness in video recognition tasks is hampered by two main challenges. Firs…

Adversarial RobustnessVideo Recognition