Related papers: Mitigating Low-Frequency Bias: Feature Recalibrati…
Adversarial training (AT) methods have been found to be effective against adversarial attacks on deep neural networks. Many variants of AT have been proposed to improve its performance. Pang et al. [1] have recently shown that incorporating…
Neural networks are known to be vulnerable to adversarial attacks -- slight but carefully constructed perturbations of the inputs which can drastically impair the network's performance. Many defense methods have been proposed for improving…
Adversarial Training (AT) with Projected Gradient Descent (PGD) is an effective approach for improving the robustness of the deep neural networks. However, PGD AT has been shown to suffer from two main limitations: i) high computational…
Recent studies have shown that deep learning-based hyperspectral image (HSI) classification models are highly vulnerable to adversarial attacks, posing significant security risks. Although most approaches attempt to enhance robustness by…
Multimodal large language models (MLLMs) remain vulnerable to transfer-based targeted attacks, where perturbations optimized on open-source surrogate encoders can generalize to closed-source MLLMs. A key challenge for improving adversarial…
This paper addresses the tradeoff between standard accuracy on clean examples and robustness against adversarial examples in deep neural networks (DNNs). Although adversarial training (AT) improves robustness, it degrades the standard…
Regularization techniques such as L2 regularization (Weight Decay) and Dropout are fundamental to training deep neural networks, yet their underlying physical mechanisms regarding feature frequency selection remain poorly understood. In…
Adversarial training (AT) is currently one of the most effective ways to obtain the robustness of deep neural networks against adversarial attacks. However, most AT methods suffer from robust overfitting, i.e., a significant generalization…
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. In addition, recent…
Deep neural networks are susceptible to adversarial attacks, which can compromise their performance and accuracy. Adversarial Training (AT) has emerged as a popular approach for protecting neural networks against such attacks. However, a…
The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application. Among many developed defense models against such attacks, adversarial training emerges…
Adversarial training (AT) aims to improve the robustness of deep learning models by mixing clean data and adversarial examples (AEs). Most existing AT approaches can be grouped into restricted and unrestricted approaches. Restricted AT…
Image editing techniques enable people to modify the content of an image without leaving visual traces and thus may cause serious security risks. Hence the detection and localization of these forgeries become quite necessary and…
Despite the enormous success of artificial neural networks (ANNs) in many disciplines, the characterization of their computations and the origin of key properties such as generalization and robustness remain open questions. Recent…
Deep Learning (DL) has shown potential in accelerating Magnetic Resonance Image acquisition and reconstruction. Nevertheless, there is a dearth of tailored methods to guarantee that the reconstruction of small features is achieved with high…
Dynamic Facial Expression Recognition (DFER) plays a critical role in affective computing and human-computer interaction. Although existing methods achieve comparable performance, they inevitably suffer from performance degradation under…
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 predictions. Conversely,…
Few-shot learning (FSL) based on manifold regularization aims to improve the recognition capacity of novel objects with limited training samples by mixing two samples from different categories with a blending factor. However, this mixing…
Large vision models have been found vulnerable to adversarial examples, emphasizing the need for enhancing their adversarial robustness. While adversarial training is an effective defense for deep convolutional models, it often faces…
State-of-the-art video deblurring methods use deep network architectures to recover sharpened video frames. Blurring especially degrades high-frequency (HF) information, yet this aspect is often overlooked by recent models that focus more…