Related papers: Mitigating large adversarial perturbations on X-MA…
Recent studies have highlighted audio adversarial examples as a ubiquitous threat to state-of-the-art automatic speech recognition systems. Thorough studies on how to effectively generate adversarial examples are essential to prevent…
The phenomenon of adversarial examples in deep learning models has caused substantial concern over their reliability. While many deep neural networks have shown impressive performance in terms of predictive accuracy, it has been shown that…
Training a classifier over a large number of classes, known as 'extreme classification', has become a topic of major interest with applications in technology, science, and e-commerce. Traditional softmax regression induces a gradient cost…
Deep learning has emerged as a powerful approach for malware detection, demonstrating impressive accuracy across various data representations. However, these models face critical limitations in real-world, non-stationary environments where…
It has been well demonstrated that adversarial examples, i.e., natural images with visually imperceptible perturbations added, generally exist for deep networks to fail on image classification. In this paper, we extend adversarial examples…
Deep learning algorithms have increasingly been shown to lack robustness to simple adversarial examples (AdvX). An equally troubling observation is that these adversarial examples transfer between different architectures trained on…
Adversarial attacks insert small, imperceptible perturbations to input samples that cause large, undesired changes to the output of deep learning models. Despite extensive research on generating adversarial attacks and building defense…
Perturbative anticrossings have long been identified as a potential computational bottleneck for quantum annealing. This bottleneck can appear, for example, when a uniform transverse driver Hamiltonian is applied to each qubit. Previous…
Adversarial training has emerged as an effective approach to train robust neural network models that are resistant to adversarial attacks, even in low-label regimes where labeled data is scarce. In this paper, we introduce a novel…
We give a fast, spectral procedure for implementing approximate-message passing (AMP) algorithms robustly. For any quadratic optimization problem over symmetric matrices $X$ with independent subgaussian entries, and any separable AMP…
Unsupervised contrastive learning has shown significant performance improvements in recent years, often approaching or even rivaling supervised learning in various tasks. However, its learning mechanism is fundamentally different from…
There are a number of hypotheses underlying the existence of adversarial examples for classification problems. These include the high-dimensionality of the data, high codimension in the ambient space of the data manifolds of interest, and…
Multi-modal foundation models align images, text, and other modalities in a shared embedding space but remain vulnerable to adversarial illusions [35], where imperceptible perturbations disrupt cross-modal alignment and mislead downstream…
Studying adversarial attacks on point clouds is essential for evaluating and improving the robustness of 3D deep learning models. However, most existing attack methods are developed under ideal white-box settings and often suffer from…
Adversarial attack perturbs an image with an imperceptible noise, leading to incorrect model prediction. Recently, a few works showed inherent bias associated with such attack (robustness bias), where certain subgroups in a dataset (e.g.…
The design of additive imperceptible perturbations to the inputs of deep classifiers to maximize their misclassification rates is a central focus of adversarial machine learning. An alternative approach is to synthesize adversarial examples…
Deep neural networks can be easily fooled into making incorrect predictions through corruption of the input by adversarial perturbations: human-imperceptible artificial noise. So far adversarial training has been the most successful defense…
Adversarial training serves as one of the most popular and effective methods to defend against adversarial perturbations. However, most defense mechanisms only consider a single type of perturbation while various attack methods might be…
We propose a scheme for defending against adversarial attacks by suppressing the largest eigenvalue of the Fisher information matrix (FIM). Our starting point is one explanation on the rationale of adversarial examples. Based on the idea of…
Despite the empirical success in various domains, it has been revealed that deep neural networks are vulnerable to maliciously perturbed input data that much degrade their performance. This is known as adversarial attacks. To counter…