Results 61 to 70 of about 3,240,231 (313)
Adversarial Robustness in High-Dimensional Deep Learning [PDF]
, 2021 © 2021 Gregory Jeremiah KaranikasAs applications of deep learning continue to be discovered and implemented, the problem of robustness becomes increasingly important.
Karanikas, Gregory Jeremiah
core +1 more source
Adversarial Robustness of Model Sets [PDF]
2020 International Joint Conference on Neural Networks (IJCNN), 2020 Machine learning models are vulnerable to very small adversarial input perturbations. Here, we study the question of whether the list of predictions made by a list of models can also be changed arbitrarily by a single small perturbation. Clearly, this is a harder problem since one has to simultaneously mislead several models using the same perturbation,
István Megyeri +2 more
openaire +3 more sources
Pre-Trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness [PDF]
Computer Vision and Pattern RecognitionLarge-scale pre-trained vision-language models like CLIP have demonstrated impressive performance across various tasks, and exhibit remarkable zero-shot generalization capability, while they are also vulnerable to impercep-tible adversarial examples ...
Sibo Wang +3 more
semanticscholar +1 more source
Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients [PDF]
AAAI Conference on Artificial Intelligence, 2017 Deep neural networks have proven remarkably effective at solving many classification problems, but have been criticized recently for two major weaknesses: the reasons behind their predictions are uninterpretable, and the predictions themselves can ...
A. Ross, Finale Doshi-Velez
semanticscholar +1 more source
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
Can Large Language Models Improve the Adversarial Robustness of Graph Neural Networks? [PDF]
Knowledge Discovery and Data MiningGraph neural networks (GNNs) are vulnerable to adversarial attacks, especially for topology perturbations, and many methods that improve the robustness of GNNs have received considerable attention.
Zhongjian Zhang +6 more
semanticscholar +1 more source
On the Adversarial Robustness of Multivariate Robust Estimation
CoRR, 2019 In this paper, we investigate the adversarial robustness of multivariate $M$-Estimators. In the considered model, after observing the whole dataset, an adversary can modify all data points with the goal of maximizing inference errors. We use adversarial influence function (AIF) to measure the asymptotic rate at which the adversary can change the ...
Erhan Bayraktar, Lifeng Lai
openaire +3 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 +3 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