中文
相关论文

相关论文: A comment on Guo et al. [arXiv:2206.11228]

200 篇论文

A counter-intuitive property of convolutional neural networks (CNNs) is their inherent susceptibility to adversarial examples, which severely hinders the application of CNNs in security-critical fields. Adversarial examples are similar to…

机器学习 · 计算机科学 2022-07-27 Jiebao Zhang , Wenhua Qian , Rencan Nie , Jinde Cao , Dan Xu

As humans, we inherently perceive images based on their predominant features, and ignore noise embedded within lower bit planes. On the contrary, Deep Neural Networks are known to confidently misclassify images corrupted with meticulously…

计算机视觉与模式识别 · 计算机科学 2020-04-02 Sravanti Addepalli , Vivek B. S. , Arya Baburaj , Gaurang Sriramanan , R. Venkatesh Babu

Deep neural networks are vulnerable to adversarial examples - small input perturbations that result in incorrect predictions. We study this problem for models of source code, where we want the network to be robust to source-code…

机器学习 · 计算机科学 2022-08-23 Goutham Ramakrishnan , Jordan Henkel , Zi Wang , Aws Albarghouthi , Somesh Jha , Thomas Reps

Deep neural networks have been shown to lack robustness to small input perturbations. The process of generating the perturbations that expose the lack of robustness of neural networks is known as adversarial input generation. This process…

机器学习 · 计算机科学 2019-03-26 Tommaso Dreossi , Shromona Ghosh , Alberto Sangiovanni-Vincentelli , Sanjit A. Seshia

We consider the problem of the stability of saliency-based explanations of Neural Network predictions under adversarial attacks in a classification task. Saliency interpretations of deterministic Neural Networks are remarkably brittle even…

机器学习 · 计算机科学 2022-05-06 Ginevra Carbone , Guido Sanguinetti , Luca Bortolussi

Recent results show that features of adversarially trained networks for classification, in addition to being robust, enable desirable properties such as invertibility. The latter property may seem counter-intuitive as it is widely accepted…

机器学习 · 计算机科学 2020-12-17 Matteo Terzi , Alessandro Achille , Marco Maggipinto , Gian Antonio Susto

It is well known that deep neural networks (DNNs) are vulnerable to adversarial attacks, which are implemented by adding crafted perturbations onto benign examples. Min-max robust optimization based adversarial training can provide a notion…

计算机视觉与模式识别 · 计算机科学 2021-06-23 Shaokai Ye , Kaidi Xu , Sijia Liu , Jan-Henrik Lambrechts , Huan Zhang , Aojun Zhou , Kaisheng Ma , Yanzhi Wang , Xue Lin

This paper tackles the problem of defending a neural network against adversarial attacks crafted with different norms (in particular $\ell_\infty$ and $\ell_2$ bounded adversarial examples). It has been observed that defense mechanisms…

机器学习 · 计算机科学 2020-02-14 Alexandre Araujo , Laurent Meunier , Rafael Pinot , Benjamin Negrevergne

Deep Neural Networks (DNNs) have demonstrated exceptional performance on most recognition tasks such as image classification and segmentation. However, they have also been shown to be vulnerable to adversarial examples. This phenomenon has…

计算机视觉与模式识别 · 计算机科学 2018-07-10 Anurag Arnab , Ondrej Miksik , Philip H. S. Torr

The incredible effectiveness of adversarial attacks on fooling deep neural networks poses a tremendous hurdle in the widespread adoption of deep learning in safety and security-critical domains. While adversarial defense mechanisms have…

机器学习 · 计算机科学 2020-11-20 Hossein Aboutalebi , Mohammad Javad Shafiee Alexander Wong

Reinforcement learning policies based on deep neural networks are vulnerable to imperceptible adversarial perturbations to their inputs, in much the same way as neural network image classifiers. Recent work has proposed several methods to…

机器学习 · 计算机科学 2021-08-31 Ezgi Korkmaz

Deep reinforcement learning techniques have demonstrated superior performance in a wide variety of environments. As improvements in training algorithms continue at a brisk pace, theoretical or empirical studies on understanding what these…

机器学习 · 计算机科学 2018-11-16 Raghuram Mandyam Annasamy , Katia Sycara

In this paper we aim to explore the general robustness of neural network classifiers by utilizing adversarial as well as natural perturbations. Different from previous works which mainly focus on studying the robustness of neural networks…

计算机视觉与模式识别 · 计算机科学 2020-10-06 Sadaf Gulshad , Jan Hendrik Metzen , Arnold Smeulders

The increasing use of deep neural networks (DNNs) has motivated a parallel endeavor: the design of adversaries that profit from successful misclassifications. However, not all adversarial examples are crafted for malicious purposes. For…

计算机视觉与模式识别 · 计算机科学 2024-09-18 Pk Douglas , Farzad Vasheghani Farahani

Convolutional neural networks have been used to achieve a string of successes during recent years, but their lack of interpretability remains a serious issue. Adversarial examples are designed to deliberately fool neural networks into…

机器学习 · 计算机科学 2020-04-28 Jan Philip Göpfert , André Artelt , Heiko Wersing , Barbara Hammer

Some recent artificial neural networks (ANNs) claim to model aspects of primate neural and human performance data. Their success in object recognition is, however, dependent on exploiting low-level features for solving visual tasks in a way…

计算机视觉与模式识别 · 计算机科学 2023-04-13 Girik Malik , Dakarai Crowder , Ennio Mingolla

A convolutional neural network strongly robust to adversarial perturbations at reasonable computational and performance cost has not yet been demonstrated. The primate visual ventral stream seems to be robust to small perturbations in…

机器学习 · 计算机科学 2020-07-01 Manish V. Reddy , Andrzej Banburski , Nishka Pant , Tomaso Poggio

Current deep neural networks (DNNs) are vulnerable to adversarial attacks, where adversarial perturbations to the inputs can change or manipulate classification. To defend against such attacks, an effective and popular approach, known as…

机器学习 · 计算机科学 2022-09-08 Gaoyuan Zhang , Songtao Lu , Yihua Zhang , Xiangyi Chen , Pin-Yu Chen , Quanfu Fan , Lee Martie , Lior Horesh , Mingyi Hong , Sijia Liu

Deep convolutional neural networks (DCNNs) have revolutionized computer vision and are often advocated as good models of the human visual system. However, there are currently many shortcomings of DCNNs, which preclude them as a model of…

计算机视觉与模式识别 · 计算机科学 2022-05-19 Harshitha Machiraju , Oh-Hyeon Choung , Michael H. Herzog , Pascal Frossard

Deep neural networks have been shown to perform well in many classical machine learning problems, especially in image classification tasks. However, researchers have found that neural networks can be easily fooled, and they are surprisingly…

计算机视觉与模式识别 · 计算机科学 2019-05-24 Huaxia Wang , Chun-Nam Yu