Related papers: Spectrum Focused Frequency Adversarial Attacks for…
Adversarial attacks are inputs that are similar to original inputs but altered on purpose. Speech-to-text neural networks that are widely used today are prone to misclassify adversarial attacks. In this study, first, we investigate the…
Transfer learning across domains with distribution shift remains a fundamental challenge in building robust and adaptable machine learning systems. While adversarial perturbations are traditionally viewed as threats that expose model…
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…
Deep learning models continue to advance in accuracy, yet they remain vulnerable to adversarial attacks, which often lead to the misclassification of adversarial examples. Adversarial training is used to mitigate this problem by increasing…
Medical imaging AI systems such as disease classification and segmentation are increasingly inspired and transformed from computer vision based AI systems. Although an array of adversarial training and/or loss function based defense…
The rapid advancement of artificial intelligence within the realm of cybersecurity raises significant security concerns. The vulnerability of deep learning models in adversarial attacks is one of the major issues. In adversarial machine…
Automatic modulation classification (AMC) is to identify the modulation format of the received signal corrupted by the channel effects and noise. Most existing works focus on the impact of noise while relatively little attention has been…
This work studies black-box adversarial attacks against deep neural networks (DNNs), where the attacker can only access the query feedback returned by the attacked DNN model, while other information such as model parameters or the training…
Quantized neural networks (QNNs) have received increasing attention in resource-constrained scenarios due to their exceptional generalizability. However, their robustness against realistic black-box adversarial attacks has not been…
In this paper, we propose a novel adaptive modulation and coding (AMC) algorithm dedicated to reduce the feedback frequency of the channel state information (CSI). There have been already plenty of works on AMC so as to exploit the…
Multi-modal models have gained significant attention due to their powerful capabilities. These models effectively align embeddings across diverse data modalities, showcasing superior performance in downstream tasks compared to their…
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…
The emergence of deep learning led to the broad usage of neural networks in the time series domain for various applications, including finance and medicine. While powerful, these models are prone to adversarial attacks: a benign targeted…
Extensive research demonstrates that Deep Reinforcement Learning (DRL) models are susceptible to adversarially constructed inputs (i.e., adversarial examples), which can mislead the agent to take suboptimal or unsafe actions. Recent methods…
Machine Learning systems are vulnerable to adversarial attacks and will highly likely produce incorrect outputs under these attacks. There are white-box and black-box attacks regarding to adversary's access level to the victim learning…
Audio deepfakes pose significant threats, including impersonation, fraud, and reputation damage. To address these risks, audio deepfake detection (ADD) techniques have been developed, demonstrating success on benchmarks like ASVspoof2019.…
Current neural-network-based classifiers are susceptible to adversarial examples. The most empirically successful approach to defending against such adversarial examples is adversarial training, which incorporates a strong self-attack…
This work presents blind constrained constant modulus (CCM) adaptive algorithms based on the set-membership filtering (SMF) concept and incorporates dynamic bounds {for interference suppression} applications. We develop stochastic gradient…
The vulnerability of deep neural networks to adversarial samples has been a major impediment to their broad applications, despite their success in various fields. Recently, some works suggested that adversarially-trained models emphasize…
Supervised learning-based adversarial attack detection methods rely on a large number of labeled data and suffer significant performance degradation when applying the trained model to new domains. In this paper, we propose a self-supervised…