中文
相关论文

相关论文: GradDiv: Adversarial Robustness of Randomized Neur…

200 篇论文

In this paper, we propose a novel normalization method called gradient normalization (GN) to tackle the training instability of Generative Adversarial Networks (GANs) caused by the sharp gradient space. Unlike existing work such as gradient…

机器学习 · 计算机科学 2021-10-12 Yi-Lun Wu , Hong-Han Shuai , Zhi-Rui Tam , Hong-Yu Chiu

Adversarial robustness is considered as a required property of deep neural networks. In this study, we discover that adversarially trained models might have significantly different characteristics in terms of margin and smoothness, even…

机器学习 · 计算机科学 2021-08-26 Hoki Kim , Woojin Lee , Sungyoon Lee , Jaewook Lee

Progress in making neural networks more robust against adversarial attacks is mostly marginal, despite the great efforts of the research community. Moreover, the robustness evaluation is often imprecise, making it difficult to identify…

机器学习 · 计算机科学 2021-05-26 Leo Schwinn , René Raab , An Nguyen , Dario Zanca , Bjoern Eskofier

In recent years, deep neural networks demonstrated state-of-the-art performance in a large variety of tasks and therefore have been adopted in many applications. On the other hand, the latest studies revealed that neural networks are…

计算机视觉与模式识别 · 计算机科学 2018-12-07 Jingyang Zhang , Hsin-Pai Cheng , Chunpeng Wu , Hai Li , Yiran Chen

Deep neural networks (DNNs) are vulnerable to adversarial examples obtained by adding small perturbations to original examples. The added perturbations in existing attacks are mainly determined by the gradient of the loss function with…

密码学与安全 · 计算机科学 2023-06-06 Chen Wan , Fangjun Huang

The vulnerability of neural network classifiers to adversarial attacks is a major obstacle to their deployment in safety-critical applications. Regularization of network parameters during training can be used to improve adversarial…

机器学习 · 计算机科学 2024-05-28 Sheng Yang , Jacob A. Zavatone-Veth , Cengiz Pehlevan

This work investigates a novel approach to boost adversarial robustness and generalization by incorporating structural prior into the design of deep learning models. Specifically, our study surprisingly reveals that existing dictionary…

机器学习 · 计算机科学 2025-02-04 Zhichao Hou , Weizhi Gao , Hamid Krim , Xiaorui Liu

As designers of artificial intelligence try to outwit hackers, both sides continue to hone in on AI's inherent vulnerabilities. Designed and trained from certain statistical distributions of data, AI's deep neural networks (DNNs) remain…

计算机视觉与模式识别 · 计算机科学 2022-04-25 Wenzhao Xiang , Hang Su , Chang Liu , Yandong Guo , Shibao Zheng

Vision transformers (ViTs) have been successfully deployed in a variety of computer vision tasks, but they are still vulnerable to adversarial samples. Transfer-based attacks use a local model to generate adversarial samples and directly…

计算机视觉与模式识别 · 计算机科学 2023-06-06 Jianping Zhang , Yizhan Huang , Weibin Wu , Michael R. Lyu

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…

机器学习 · 计算机科学 2020-07-13 Anh Bui , Trung Le , He Zhao , Paul Montague , Olivier deVel , Tamas Abraham , Dinh Phung

Neural networks are vulnerable to adversarially-constructed perturbations of their inputs. Most research so far has considered perturbations of a fixed magnitude under some $l_p$ norm. Although studying these attacks is valuable, there has…

机器学习 · 计算机科学 2019-10-02 Isaac Dunn , Hadrien Pouget , Tom Melham , Daniel Kroening

The vulnerability of neural networks under adversarial attacks has raised serious concerns and motivated extensive research. It has been shown that both neural networks and adversarial attacks against them can be sensitive to input…

计算机视觉与模式识别 · 计算机科学 2019-06-17 Houpu Yao , Zhe Wang , Guangyu Nie , Yassine Mazboudi , Yezhou Yang , Yi Ren

A major obstacle to achieving global convergence in distributed and federated learning is the misalignment of gradients across clients, or mini-batches due to heterogeneity and stochasticity of the distributed data. In this work, we show…

机器学习 · 计算机科学 2021-12-14 Yatin Dandi , Luis Barba , Martin Jaggi

Deep neural networks are known to be vulnerable to adversarial attacks. Current methods of defense from such attacks are based on either implicit or explicit regularization, e.g., adversarial training. Randomized smoothing, the averaging of…

Deep neural networks are a promising approach towards multi-task learning because of their capability to leverage knowledge across domains and learn general purpose representations. Nevertheless, they can fail to live up to these promises…

机器学习 · 计算机科学 2019-12-17 Mihai Suteu , Yike Guo

The two key players in Generative Adversarial Networks (GANs), the discriminator and generator, are usually parameterized as deep neural networks (DNNs). On many generative tasks, GANs achieve state-of-the-art performance but are often…

机器学习 · 计算机科学 2019-01-31 Babajide O. Ayinde , Keishin Nishihama , Jacek M. Zurada

Deep neural networks are capable of training fast and generalizing well within many domains. Despite their promising performance, deep networks have shown sensitivities to perturbations of their inputs (e.g., adversarial examples) and their…

机器学习 · 计算机科学 2020-07-09 Justin Goodwin , Olivia Brown , Victoria Helus

Deep neural network image classifiers are known to be susceptible not only to adversarial examples created for them but even those created for others. This phenomenon poses a potential security risk in various black-box systems relying on…

计算机视觉与模式识别 · 计算机科学 2021-09-14 Kevin Richard G. Operiano , Wanchalerm Pora , Hitoshi Iba , Hiroshi Kera

Deep neural networks (DNNs) have been widely used in many fields such as images processing, speech recognition; however, they are vulnerable to adversarial examples, and this is a security issue worthy of attention. Because the training…

密码学与安全 · 计算机科学 2019-08-08 Wenjian Luo , Chenwang Wu , Nan Zhou , Li Ni

Vulnerability to adversarial attacks is one of the principal hurdles to the adoption of deep learning in safety-critical applications. Despite significant efforts, both practical and theoretical, training deep learning models robust to…

机器学习 · 计算机科学 2024-02-29 Luca Bortolussi , Ginevra Carbone , Luca Laurenti , Andrea Patane , Guido Sanguinetti , Matthew Wicker