相关论文: The Effects of Image Distribution and Task on Adve…

Although distributed machine learning (distributed ML) is gaining considerable attention in the community, prior works have independently looked at instances of distributed ML in either the training or the inference phase. No prior work has…

Adversarial training can improve the robustness of neural networks. Previous methods focus on a single adversarial training strategy and do not consider the model property trained by different strategies. By revisiting the previous methods,…

As deep learning models continue to advance and are increasingly utilized in real-world systems, the issue of robustness remains a major challenge. Existing certified training methods produce models that achieve high provable robustness…

In learning problems, the noise inherent to the task at hand hinders the possibility to infer without a certain degree of uncertainty. Quantifying this uncertainty, regardless of its wide use, assumes high relevance for security-sensitive…

While many defences against adversarial examples have been proposed, finding robust machine learning models is still an open problem. The most compelling defence to date is adversarial training and consists of complementing the training…

Adversarial training and its many variants substantially improve deep network robustness, yet at the cost of compromising standard accuracy. Moreover, the training process is heavy and hence it becomes impractical to thoroughly explore the…

Adversarial robustness corresponds to the susceptibility of deep neural networks to imperceptible perturbations made at test time. In the context of image tasks, many algorithms have been proposed to make neural networks robust to…

Deep neural networks (DNNs) are vulnerable to malicious inputs crafted by an adversary to produce erroneous outputs. Works on securing neural networks against adversarial examples achieve high empirical robustness on simple datasets such as…

Adversarial pruning compresses models while preserving robustness. Current methods require access to adversarial examples during pruning. This significantly hampers training efficiency. Moreover, as new adversarial attacks and training…

Deep neural networks have achieved impressive performance on a variety of tasks, but their brittleness to distributional shifts remains a significant barrier to real-world deployment. In this paper, we propose a framework to analyse and…

In this paper, we aim to understand and explain the decisions of deep neural networks by studying the behavior of predicted attributes when adversarial examples are introduced. We study the changes in attributes for clean as well as…

This paper proposes an attack-independent (non-adversarial training) technique for improving adversarial robustness of neural network models, with minimal loss of standard accuracy. We suggest creating a neighborhood around each training…

Recent studies have demonstrated that visual recognition models lack robustness to distribution shift. However, current work mainly considers model robustness to 2D image transformations, leaving viewpoint changes in the 3D world less…

Despite strong performance in numerous applications, the fragility of deep learning to input perturbations has raised serious questions about its use in safety-critical domains. While adversarial training can mitigate this issue in…

Despite vast research in adversarial examples, the root causes of model susceptibility are not well understood. Instead of looking at attack-specific robustness, we propose a notion that evaluates the sensitivity of individual neurons in…

Several recent works have developed methods for training classifiers that are certifiably robust against norm-bounded adversarial perturbations. These methods assume that all the adversarial transformations are equally important, which is…

Deep neural networks (DNNs) are powerful nonlinear architectures that are known to be robust to random perturbations of the input. However, these models are vulnerable to adversarial perturbations--small input changes crafted explicitly to…

Previous work on adversarially robust neural networks for image classification requires large training sets and computationally expensive training procedures. On the other hand, few-shot learning methods are highly vulnerable to adversarial…

This paper investigates the resilience of perception-based multi-robot coordination with wireless communication to online adversarial perception. A systematic study of this problem is essential for many safety-critical robotic applications…

Despite substantial advances in network architecture performance, the susceptibility of adversarial attacks makes deep learning challenging to implement in safety-critical applications. This paper proposes a data-centric approach to…