Results 51 to 60 of about 2,268,403 (339)

Benchmarking Adversarial Robustness

, 2019
Deep neural networks are vulnerable to adversarial examples, which becomes one of the most important research problems in the development of deep learning. While a lot of efforts have been made in recent years, it is of great significance to perform correct and complete evaluations of the adversarial attack and defense algorithms.
Dong, Yinpeng, Fu, Qi-An, Yang, Xiao, Pang, Tianyu, Su, Hang, Xiao, Zihao, Zhu, Jun   +6 more
openaire   +2 more sources

Triple Down on Robustness: Understanding the Impact of Adversarial Triplet Compositions on Adversarial Robustness

Machine Learning and Knowledge Extraction
Adversarial training, a widely used technique for fortifying the robustness of machine learning models, has seen its effectiveness further bolstered by modifying loss functions or incorporating additional terms into the training objective.
Sander Joos, Tim Van hamme, Willem Verheyen, Davy Preuveneers, Wouter Joosen   +4 more
doaj   +1 more source

Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Models

, 2019
The prediction accuracy has been the long-lasting and sole standard for comparing the performance of different image classification models, including the ImageNet competition.
Su, Dong, Zhang, Huan, Chen, Hongge, Yi, Jinfeng, Chen, Pin-Yu, Gao, Yupeng   +5 more
core   +1 more source

Adversarially Robust Neural Architectures

IEEE Transactions on Pattern Analysis and Machine Intelligence
13 pages, 5 figures, 8 ...
Minjing Dong, Yanxi Li, Yunhe Wang, Chang Xu   +3 more
openaire   +3 more sources

Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial Robustness

, 2022
Accepted by ECCV 2022 oral ...
Zhang, Chaoning, Zhang, Kang, Zhang, Chenshuang, Niu, Axi, Feng, Jiu, Yoo, Chang D., Kweon, In So   +6 more
openaire   +2 more sources

A Comparative Study on the Performance and Security Evaluation of Spiking Neural Networks

IEEE Access, 2022
The brain-inspired Spiking neural networks (SNN) claim to present advantages for visual classification tasks in terms of energy efficiency and inherent robustness.
Yanjie Li, Xiaoxin Cui, Yihao Zhou, Ying Li   +3 more
doaj   +1 more source

Disentangling Adversarial Robustness and Generalization

, 2019
Obtaining deep networks that are robust against adversarial examples and generalize well is an open problem. A recent hypothesis even states that both robust and accurate models are impossible, i.e., adversarial robustness and generalization are ...
Hein, Matthias, Schiele, Bernt, Stutz, David   +2 more
core   +1 more source

Adversarial Robustness: Softmax versus Openmax

, 2017
Deep neural networks (DNNs) provide state-of-the-art results on various tasks and are widely used in real world applications. However, it was discovered that machine learning models, including the best performing DNNs, suffer from a fundamental problem ...
Boult, Terrance E., Günther, Manuel, Rozsa, Andras   +2 more
core   +1 more source

Analysis of classifiers' robustness to adversarial perturbations

, 2016
The goal of this paper is to analyze an intriguing phenomenon recently discovered in deep networks, namely their instability to adversarial perturbations (Szegedy et. al., 2014).
Fawzi, Alhussein, Fawzi, Omar, Frossard, Pascal   +2 more
core   +1 more source

Understanding the Energy vs. Adversarial Robustness Trade-Off in Deep Neural Networks

IEEE Open Journal of Circuits and Systems, 2021
Adversarial examples, which are crafted by adding small perturbations to typical inputs in order to fool the prediction of a deep neural network (DNN), pose a threat to security-critical applications, and robustness against adversarial examples is ...
Kyungmi Lee, Anantha P. Chandrakasan
doaj   +1 more source