中文
相关论文

相关论文: On damage of interpolation to adversarial robustne…

200 篇论文

Following the recent adoption of deep neural networks (DNN) accross a wide range of applications, adversarial attacks against these models have proven to be an indisputable threat. Adversarial samples are crafted with a deliberate intention…

机器学习 · 计算机科学 2017-08-31 Valentina Zantedeschi , Maria-Irina Nicolae , Ambrish Rawat

Deep neural networks (DNNs) achieve impressive results for complicated tasks like object detection on images and speech recognition. Motivated by this practical success, there is now a strong interest in showing good theoretical properties…

机器学习 · 统计学 2020-06-16 Michael Kohler , Adam Krzyzak , Sophie Langer

Despite the efficacy on a variety of computer vision tasks, deep neural networks (DNNs) are vulnerable to adversarial attacks, limiting their applications in security-critical systems. Recent works have shown the possibility of generating…

计算机视觉与模式识别 · 计算机科学 2018-12-21 Ziang Yan , Yiwen Guo , Changshui Zhang

From tiny pacemaker chips to aircraft collision avoidance systems, the state-of-the-art Cyber-Physical Systems (CPS) have increasingly started to rely on Deep Neural Networks (DNNs). However, as concluded in various studies, DNNs are highly…

密码学与安全 · 计算机科学 2021-05-10 Faiq Khalid , Muhammad Abdullah Hanif , Muhammad Shafique

Machine learning methods in general and Deep Neural Networks in particular have shown to be vulnerable to adversarial perturbations. So far this phenomenon has mainly been studied in the context of whole-image classification. In this…

机器学习 · 统计学 2017-03-06 Volker Fischer , Mummadi Chaithanya Kumar , Jan Hendrik Metzen , Thomas Brox

Deep Neural Networks (DNNs) are commonly used for various traffic analysis problems, such as website fingerprinting and flow correlation, as they outperform traditional (e.g., statistical) techniques by large margins. However, deep neural…

密码学与安全 · 计算机科学 2020-02-18 Milad Nasr , Alireza Bahramali , Amir Houmansadr

In this paper, we uniquely study the adversarial robustness of deep neural networks (NN) for classification tasks against that of optimal classifiers. We look at the smallest magnitude of possible additive perturbations that can change a…

机器学习 · 计算机科学 2025-11-05 Jingchao Gao , Ziqing Lu , Raghu Mudumbai , Xiaodong Wu , Jirong Yi , Myung Cho , Catherine Xu , Hui Xie , Weiyu Xu

Neural Networks (NNs) are vulnerable to adversarial examples. Such inputs differ only slightly from their benign counterparts yet provoke misclassifications of the attacked NNs. The required perturbations to craft the examples are often…

密码学与安全 · 计算机科学 2020-09-30 Philip Sperl , Konstantin Böttinger

In this study, we prove that an intrinsic low dimensionality of covariates is the main factor that determines the performance of deep neural networks (DNNs). DNNs generally provide outstanding empirical performance. Hence, numerous studies…

机器学习 · 统计学 2020-09-18 Ryumei Nakada , Masaaki Imaizumi

Deep neural networks (DNNs) are found to be vulnerable to adversarial noise. They are typically misled by adversarial samples to make wrong predictions. To alleviate this negative effect, in this paper, we investigate the dependence between…

机器学习 · 计算机科学 2022-07-26 Dawei Zhou , Nannan Wang , Xinbo Gao , Bo Han , Xiaoyu Wang , Yibing Zhan , Tongliang Liu

The vulnerability of deep neural networks against adversarial examples - inputs with small imperceptible perturbations - has gained a lot of attention in the research community recently. Simultaneously, the number of parameters of…

机器学习 · 计算机科学 2021-08-20 Florian Merkle , Maximilian Samsinger , Pascal Schöttle

Recent studies have shown that deep neural networks (DNN) are vulnerable to adversarial samples: maliciously-perturbed samples crafted to yield incorrect model outputs. Such attacks can severely undermine DNN systems, particularly in…

机器学习 · 计算机科学 2017-04-28 Ji Gao , Beilun Wang , Zeming Lin , Weilin Xu , Yanjun Qi

Deep neural networks (DNNs) have demonstrated impressive performance on a wide array of tasks, but they are usually considered opaque since internal structure and learned parameters are not interpretable. In this paper, we re-examine the…

计算机视觉与模式识别 · 计算机科学 2017-08-21 Yinpeng Dong , Hang Su , Jun Zhu , Fan Bao

As deep neural networks (DNNs) become widely used, pruned and quantised models are becoming ubiquitous on edge devices; such compressed DNNs are popular for lowering computational requirements. Meanwhile, recent studies show that…

密码学与安全 · 计算机科学 2020-04-17 Yiren Zhao , Ilia Shumailov , Robert Mullins , Ross Anderson

Machine learning (ML) models are often sensitive to carefully crafted yet seemingly unnoticeable perturbations. Such adversarial examples are considered to be a property of ML models, often associated with their black-box operation and…

机器学习 · 计算机科学 2025-04-29 Elad Sofer , Tomer Shaked , Caroline Chaux , Nir Shlezinger

Deep neural networks (DNNs) have played a key role in a wide range of machine learning applications. However, DNN classifiers are vulnerable to human-imperceptible adversarial perturbations, which can cause them to misclassify inputs with…

机器学习 · 计算机科学 2020-05-20 Jeffrey Z. Pan , Nicholas Zufelt

While deep neural networks (DNNs) have revolutionized many fields, their fragility to carefully designed adversarial attacks impedes the usage of DNNs in safety-critical applications. In this paper, we strive to explore the robust features…

计算机视觉与模式识别 · 计算机科学 2023-09-12 Hong Wang , Yuefan Deng , Shinjae Yoo , Yuewei Lin

Deep Neural Networks (DNNs) have shown remarkable performance in a diverse range of machine learning applications. However, it is widely known that DNNs are vulnerable to simple adversarial perturbations, which causes the model to…

机器学习 · 计算机科学 2021-07-23 Gihyuk Ko , Gyumin Lim

Deep neural networks have proven remarkably effective at solving many classification problems, but have been criticized recently for two major weaknesses: the reasons behind their predictions are uninterpretable, and the predictions…

机器学习 · 计算机科学 2017-11-28 Andrew Slavin Ross , Finale Doshi-Velez

Adversarial attacks have been shown to be highly effective at degrading the performance of deep neural networks (DNNs). The most prominent defense is adversarial training, a method for learning a robust model. Nevertheless, adversarial…

计算机视觉与模式识别 · 计算机科学 2021-09-07 Uriya Pesso , Koby Bibas , Meir Feder