中文
相关论文

相关论文: Defending Against Adversarial Attacks by Suppressi…

200 篇论文

Many deep learning models are vulnerable to the adversarial attack, i.e., imperceptible but intentionally-designed perturbations to the input can cause incorrect output of the networks. In this paper, using information geometry, we provide…

机器学习 · 计算机科学 2019-02-12 Chenxiao Zhao , P. Thomas Fletcher , Mixue Yu , Yaxin Peng , Guixu Zhang , Chaomin Shen

Adversarial examples are slight perturbations that are designed to fool artificial neural networks when fed as an input. In this work the usability of the Fisher information for the detection of such adversarial attacks is studied. We…

机器学习 · 计算机科学 2019-09-13 Jörg Martin , Clemens Elster

Deep neural networks are vulnerable to adversarial examples, i.e., carefully-crafted inputs that mislead classification at test time. Recent defenses have been shown to improve adversarial robustness by detecting anomalous deviations from…

机器学习 · 计算机科学 2020-10-20 Francesco Crecchi , Marco Melis , Angelo Sotgiu , Davide Bacciu , Battista Biggio

Despite recent advancements, deep neural networks are not robust against adversarial perturbations. Many of the proposed adversarial defense approaches use computationally expensive training mechanisms that do not scale to complex…

计算机视觉与模式识别 · 计算机科学 2021-04-22 Nikhil Kapoor , Andreas Bär , Serin Varghese , Jan David Schneider , Fabian Hüger , Peter Schlicht , Tim Fingscheidt

The Fisher information matrix (FIM) plays an essential role in statistics and machine learning as a Riemannian metric tensor or a component of the Hessian matrix of loss functions. Focusing on the FIM and its variants in deep neural…

机器学习 · 统计学 2020-09-29 Ryo Karakida , Shotaro Akaho , Shun-ichi Amari

Machine learning models have demonstrated vulnerability to adversarial attacks, more specifically misclassification of adversarial examples. In this paper, we propose a one-off and attack-agnostic Feature Manipulation (FM)-Defense to detect…

机器学习 · 计算机科学 2020-04-23 Shuo Wang , Tianle Chen , Surya Nepal , Carsten Rudolph , Marthie Grobler , Shangyu Chen

In the realm of deep learning, the Fisher information matrix (FIM) gives novel insights and useful tools to characterize the loss landscape, perform second-order optimization, and build geometric learning theories. The exact FIM is either…

机器学习 · 计算机科学 2021-10-29 Alexander Soen , Ke Sun

Though deep neural networks have achieved state-of-the-art performance in visual classification, recent studies have shown that they are all vulnerable to the attack of adversarial examples. Small and often imperceptible perturbations to…

机器学习 · 计算机科学 2018-06-05 Pinlong Zhao , Zhouyu Fu , Ou wu , Qinghua Hu , Jun Wang

Vision-Language Models (VLMs) inherit adversarial vulnerabilities of Large Language Models (LLMs), which are further exacerbated by their multimodal nature. Existing defenses, including adversarial training, input transformations, and…

The superiority of deep learning performance is threatened by safety issues for itself. Recent findings have shown that deep learning systems are very weak to adversarial examples, an attack form that was altered by the attacker's intent to…

计算机视觉与模式识别 · 计算机科学 2020-03-06 Dang Duy Thang , Toshihiro Matsui

Despite the fact that deep neural networks (DNNs) have achieved prominent performance in various applications, it is well known that DNNs are vulnerable to adversarial examples/samples (AEs) with imperceptible perturbations in…

计算机视觉与模式识别 · 计算机科学 2021-11-22 Yanni Li , Wenhui Zhang , Jiawei Liu , Xiaoli Kou , Hui Li , Jiangtao Cui

Deep Learning based AI systems have shown great promise in various domains such as vision, audio, autonomous systems (vehicles, drones), etc. Recent research on neural networks has shown the susceptibility of deep networks to adversarial…

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 Fisher information matrix (FIM) is a fundamental quantity to represent the characteristics of a stochastic model, including deep neural networks (DNNs). The present study reveals novel statistics of FIM that are universal among a wide…

机器学习 · 统计学 2019-10-10 Ryo Karakida , Shotaro Akaho , Shun-ichi Amari

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

Studies on backdoor attacks in recent years suggest that an adversary can compromise the integrity of a deep neural network (DNN) by manipulating a small set of training samples. Our analysis shows that such manipulation can make the…

计算机视觉与模式识别 · 计算机科学 2024-09-04 Nazmul Karim , Abdullah Al Arafat , Adnan Siraj Rakin , Zhishan Guo , Nazanin Rahnavard

Adversarial attacks on deep-learning models pose a serious threat to their reliability and security. Existing defense mechanisms are narrow addressing a specific type of attack or being vulnerable to sophisticated attacks. We propose a new…

机器学习 · 计算机科学 2023-06-22 Mouna Rabhi , Roberto Di Pietro

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

Adversarial robustness has become a topic of growing interest in machine learning since it was observed that neural networks tend to be brittle. We propose an information-geometric formulation of adversarial defense and introduce FIRE, a…

机器学习 · 计算机科学 2022-06-15 Marine Picot , Francisco Messina , Malik Boudiaf , Fabrice Labeau , Ismail Ben Ayed , Pablo Piantanida

Generating and eliminating adversarial examples has been an intriguing topic in the field of deep learning. While previous research verified that adversarial attacks are often fragile and can be defended via image-level processing, it…

机器学习 · 计算机科学 2019-06-27 Yifeng Li , Lingxi Xie , Ya Zhang , Rui Zhang , Yanfeng Wang , Qi Tian
‹ 上一页 1 2 3 10 下一页 ›