Results 41 to 50 of about 25,829 (292)
On the Adversarial Robustness of Mixture of Experts
Advances in Neural Information Processing Systems 35, 2022 Adversarial robustness is a key desirable property of neural networks. It has been empirically shown to be affected by their sizes, with larger networks being typically more robust. Recently, Bubeck and Sellke proved a lower bound on the Lipschitz constant of functions that fit the training data in terms of their number of parameters.
Joan Puigcerver +4 more
openaire +3 more sources
On the Effect of Pruning on Adversarial Robustness [PDF]
2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2021 Published at International Conference on Computer Vision Workshop (ICCVW ...
Artur Jordão, Hélio Pedrini
openaire +2 more sources
Adversarial Robustness through Disentangled Representations
, 2021 Despite the remarkable empirical performance of deep learning models, their vulnerability to adversarial examples has been revealed in many studies. They are prone to make a susceptible prediction to the input with imperceptible adversarial perturbation.
Guo, Tianyu +3 more
core +1 more source
Benchmarking Adversarial Robustness
CoRR, 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.
Yinpeng Dong +6 more
openaire +2 more sources
Dropping Pixels for Adversarial Robustness [PDF]
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2019 Deep neural networks are vulnerable against adversarial examples. In this paper, we propose to train and test the networks with randomly subsampled images with high drop rates. We show that this approach significantly improves robustness against adversarial examples in all cases of bounded L0, L2 and L_inf perturbations, while reducing the standard ...
Hossein Hosseini +2 more
openaire +2 more sources
Feature Augmentation for Adversarial Robustness
, 2022 Adversarial attack is to craft tiny perturbations on inputs, causing neural networks to give incorrect outputs with high confidence, while adversarial training is the de facto most successful method to obtain robust neural networks.
Zhiqiang Ge (12426309) +1 more
core +1 more source
On Evaluating Adversarial Robustness
CoRR, 2019 Correctly evaluating defenses against adversarial examples has proven to be extremely difficult. Despite the significant amount of recent work attempting to design defenses that withstand adaptive attacks, few have succeeded; most papers that propose defenses are quickly shown to be incorrect. We believe a large contributing factor is the difficulty of
Nicholas Carlini +8 more
openaire +2 more sources
Squeeze Training for Adversarial Robustness
, 2022 The vulnerability of deep neural networks (DNNs) to adversarial examples has attracted great attention in the machine learning community. The problem is related to non-flatness and non-smoothness of normally obtained loss landscapes. Training augmented with adversarial examples (a.k.a., adversarial training) is considered as an effective remedy.
Qizhang Li +3 more
openaire +3 more sources
Contextual Fusion For Adversarial Robustness
CoRR, 2020 Mammalian brains handle complex reasoning tasks in a gestalt manner by integrating information from regions of the brain that are specialised to individual sensory modalities. This allows for improved robustness and better generalisation ability. In contrast, deep neural networks are usually designed to process one particular information stream and ...
Aiswarya Akumalla +2 more
openaire +2 more sources
On the Adversarial Robustness of Hypothesis Testing
IEEE Transactions on Signal Processing, 2021 In this paper, we investigate the adversarial robustness of hypothesis testing rules. In the considered model, after a sample is generated, it will be modified by an adversary before being observed by the decision maker. The decision maker needs to decide the underlying hypothesis that generates the sample from the adversarially-modified data.
Yulu Jin, Lifeng Lai
openaire +3 more sources