中文
相关论文

相关论文: Late Breaking Results: Fortifying Neural Networks:…

200 篇论文

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

It is well established that neural networks are vulnerable to adversarial examples, which are almost imperceptible on human vision and can cause the deep models misbehave. Such phenomenon may lead to severely inestimable consequences in the…

机器学习 · 计算机科学 2020-09-09 Dengpan Ye , Chuanxi Chen , Changrui Liu , Hao Wang , Shunzhi Jiang

Hundreds of defenses have been proposed to make deep neural networks robust against minimal (adversarial) input perturbations. However, only a handful of these defenses held up their claims because correctly evaluating robustness is…

机器学习 · 计算机科学 2022-06-29 Roland S. Zimmermann , Wieland Brendel , Florian Tramer , Nicholas Carlini

Recent study of adversarial attacks has revealed the vulnerability of modern deep learning models. That is, subtly crafted perturbations of the input can make a trained network with high accuracy produce arbitrary incorrect predictions,…

机器学习 · 计算机科学 2023-04-11 Xiao Wang , Siyue Wang , Pin-Yu Chen , Xue Lin , Peter Chin

Spiking Neural Networks (SNNs) have emerged as a promising alternative to traditional Deep Neural Networks for low-power computing. However, the effectiveness of SNNs is not solely determined by their performance but also by their energy…

神经与进化计算 · 计算机科学 2023-05-19 Florian Bacho , Dominique Chu

In this paper, we aim to develop a scalable algorithm to preserve differential privacy (DP) in adversarial learning for deep neural networks (DNNs), with certified robustness to adversarial examples. By leveraging the sequential composition…

密码学与安全 · 计算机科学 2020-09-16 NhatHai Phan , My T. Thai , Han Hu , Ruoming Jin , Tong Sun , Dejing Dou

As machine learning techniques become increasingly prevalent in data analysis, the threat of adversarial attacks has surged, necessitating robust defense mechanisms. Among these defenses, methods exploiting low-rank approximations for input…

机器学习 · 计算机科学 2023-09-06 Manish Bhattarai , Mehmet Cagri Kaymak , Ryan Barron , Ben Nebgen , Kim Rasmussen , Boian Alexandrov

Self-Supervised Learning (SSL) has shown great promise in learning representations from unlabeled data. The power of learning representations without the need for human annotations has made SSL a widely used technique in real-world…

计算机视觉与模式识别 · 计算机科学 2024-09-17 Aryan Satpathy , Nilaksh Singh , Dhruva Rajwade , Somesh Kumar

While deep learning has led to remarkable results on a number of challenging problems, researchers have discovered a vulnerability of neural networks in adversarial settings, where small but carefully chosen perturbations to the input can…

神经与进化计算 · 计算机科学 2018-11-26 Edward Grefenstette , Robert Stanforth , Brendan O'Donoghue , Jonathan Uesato , Grzegorz Swirszcz , Pushmeet Kohli

Deep neural networks (DNNs) have gained prominence in various applications, such as classification, recognition, and prediction, prompting increased scrutiny of their properties. A fundamental attribute of traditional DNNs is their…

机器学习 · 计算机科学 2023-08-15 Roman Garaev , Bader Rasheed , Adil Khan

An adversarial example is a modified input image designed to cause a Machine Learning (ML) model to make a mistake; these perturbations are often invisible or subtle to human observers and highlight vulnerabilities in a model's ability to…

密码学与安全 · 计算机科学 2024-11-04 Ehsan Ganjidoost , Jeff Orchard

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where an attacker manipulates a small portion of the training data to implant hidden backdoors into the model. The compromised model behaves normally on clean samples but…

密码学与安全 · 计算机科学 2026-02-20 Ting Qiao , Yingjia Wang , Xing Liu , Sixing Wu , Jianbin Li , Yiming Li

Deep neural networks have been shown to suffer from critical vulnerabilities under adversarial attacks. This phenomenon stimulated the creation of different attack and defense strategies similar to those adopted in cyberspace security. The…

密码学与安全 · 计算机科学 2021-05-07 Ruoxi Qin , Linyuan Wang , Xingyuan Chen , Xuehui Du , Bin Yan

Spiking Neural Networks (SNNs), recognized as the third generation of neural networks, are known for their bio-plausibility and energy efficiency, especially when implemented on neuromorphic hardware. However, the majority of existing…

神经与进化计算 · 计算机科学 2024-07-02 Yi Jiang , Sen Lu , Abhronil Sengupta

Achieving robustness against adversarial input perturbation is an important and intriguing problem in machine learning. In the area of semantic image segmentation, a number of adversarial training approaches have been proposed as a defense…

计算机视觉与模式识别 · 计算机科学 2023-06-27 Levente Halmosi , Mark Jelasity

With the rise in popularity of machine and deep learning models, there is an increased focus on their vulnerability to malicious inputs. These adversarial examples drift model predictions away from the original intent of the network and are…

计算机视觉与模式识别 · 计算机科学 2020-03-11 Richard Tran , David Patrick , Michael Geyer , Amanda Fernandez

Deep neural networks have achieved state-of-the-art performance in a variety of fields. Recent works observe that a class of widely used neural networks can be viewed as the Euler method of numerical discretization. From the numerical…

计算机视觉与模式识别 · 计算机科学 2020-10-21 Byungjoo Kim , Bryce Chudomelka , Jinyoung Park , Jaewoo Kang , Youngjoon Hong , Hyunwoo J. Kim

Neural networks have received a lot of attention recently, and related security issues have come with it. Many studies have shown that neural networks are vulnerable to adversarial examples that have been artificially perturbed with…

密码学与安全 · 计算机科学 2025-08-07 Shi Pu , Fu Song , Wenjie Wang

Spiking Neural Networks (SNNs) utilize spike-based activations to mimic the brain's energy-efficient information processing. However, the binary and discontinuous nature of spike activations causes vanishing gradients, making adversarial…

机器学习 · 计算机科学 2026-02-10 Jihang Wang , Dongcheng Zhao , Ruolin Chen , Qian Zhang , Yi Zeng

In this paper, we consider the problem of attack-resilient state estimation, that is to reliably estimate the true system states despite two classes of attacks: (i) attacks on the switching mechanisms and (ii) false data injection attacks…

最优化与控制 · 数学 2017-07-25 Sze Zheng Yong , Minghui Zhu , Emilio Frazzoli