Results 51 to 60 of about 3,240,231 (313)

Adversarial robustness of amortized Bayesian inference [PDF]

International Conference on Machine Learning, 2023
Bayesian inference usually requires running potentially costly inference procedures separately for every new observation. In contrast, the idea of amortized Bayesian inference is to initially invest computational cost in training an inference network on ...
Manuel Glöckler, Michael Deistler, J. Macke   +2 more
semanticscholar   +1 more source

Adversarially Robust Learning with Tolerance

CoRR, 2022
We initiate the study of tolerant adversarial PAC-learning with respect to metric perturbation sets. In adversarial PAC-learning, an adversary is allowed to replace a test point $x$ with an arbitrary point in a closed ball of radius $r$ centered at $x$.
Hassan Ashtiani, Vinayak Pathak, Ruth Urner   +2 more
openaire   +3 more sources

CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIP [PDF]

Computer Vision and Pattern Recognition
Despite its prevalent use in image-text matching tasks in a zero-shot manner, CLIP has been shown to be highly vulnerable to adversarial perturbations added onto images.
Songlong Xing, Zhengyu Zhao, N. Sebe
semanticscholar   +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, Qi-An Fu, Xiao Yang 0028, Tianyu Pang, Hang Su 0006, Zihao Xiao 0002, Jun Zhu 0001   +6 more
openaire   +2 more sources

Adversarial Detector with Robust Classifier

2022 IEEE 4th Global Conference on Life Sciences and Technologies (LifeTech), 2022
Deep neural network (DNN) models are wellknown to easily misclassify prediction results by using input images with small perturbations, called adversarial examples. In this paper, we propose a novel adversarial detector, which consists of a robust classifier and a plain one, to highly detect adversarial examples.
Takayuki Osakabe, AprilPyone MaungMaung, Sayaka Shiota, Hitoshi Kiya   +3 more
openaire   +3 more sources

Advancing Adversarial Robustness Through Adversarial Logit Update [PDF]

, 2023
Deep Neural Networks are susceptible to adversarial perturbations. Adversarial training and adversarial purification are among the most widely recognized defense strategies.
Xuan, Hao, Zhu, Peican, Li, Xingyu
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, Anish Athalye, Nicolas Papernot, Wieland Brendel, Jonas Rauber, Dimitris Tsipras, Ian J. Goodfellow, Aleksander Madry, Alexey Kurakin   +8 more
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, Xu, Chang, Yang, Shuo, Wang, Yunhe   +3 more
core   +1 more source

One Prompt Word is Enough to Boost Adversarial Robustness for Pre-Trained Vision-Language Models [PDF]

Computer Vision and Pattern Recognition
Large pre-trained Vision-Language Models (VLMs) like CLIP, despite having remarkable generalization ability, are highly vulnerable to adversarial examples. This work studies the adversarial robustness of VLMs from the novel perspective of the text prompt
Lin Li, Haoyan Guan, Jianing Qiu, Michael W. Spratling   +3 more
semanticscholar   +1 more source

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), Yue Zhuo (12426282)   +1 more
core   +1 more source