Results 71 to 80 of about 3,240,231 (313)
Wasserstein Adversarial Robustness [PDF]
, 2020 Deep models, while being extremely flexible and accurate, are surprisingly vulnerable to ``small, imperceptible'' perturbations known as adversarial attacks.
Wu, Kaiwen
core
Achieving Adversarial Robustness via Sparsity [PDF]
, 2020 Network pruning has been known to produce compact models without much accuracy degradation. However, how the pruning process affects a network's robustness and the working mechanism behind remain unresolved.
Wang, Shufan +4 more
core +1 more source
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
Are facial attributes adversarially robust? [PDF]
2016 23rd International Conference on Pattern Recognition (ICPR), 2016 Facial attributes are emerging soft biometrics that have the potential to reject non-matches, for example, based on mismatching gender. To be usable in stand-alone systems, facial attributes must be extracted from images automatically and reliably. In this paper, we propose a simple yet effective solution for automatic facial attribute extraction by ...
Andras Rozsa +3 more
openaire +3 more sources
Towards Resilient and Efficient LLMs: A Comparative Study of Efficiency, Performance, and Adversarial Robustness [PDF]
Artificial Intelligence and Cloud Computing ConferenceWith the increasing demand for practical applications of Large Language Models (LLMs), many attention-efficient models have been developed to balance performance and computational cost.
Xiaojing Fan, Chunliang Tao
semanticscholar +1 more source
Outlier Robust Adversarial Training
CoRR, 2023 Supervised learning models are challenged by the intrinsic complexities of training data such as outliers and minority subpopulations and intentional attacks at inference time with adversarial samples. While traditional robust learning methods and the recent adversarial training approaches are designed to handle each of the two challenges, to date, no ...
Shu Hu 0001 +4 more
openaire +4 more sources
Adversarial Self-Supervised Learning for Robust SAR Target Recognition
Remote Sensing, 2021 Synthetic aperture radar (SAR) can perform observations at all times and has been widely used in the military field. Deep neural network (DNN)-based SAR target recognition models have achieved great success in recent years.
Yanjie Xu +5 more
doaj +1 more source
Adversarial Robustness of Deep Neural Networks: A Survey from a Formal Verification Perspective
, 2022 Neural networks have been widely applied in security applications such as spam and phishing detection, intrusion prevention, and malware detection. This black-box method, however, often has uncertainty and poor explainability in applications. Furthermore,
Teo, SG +6 more
core +1 more source
IEEE Access, 2021 Although the hyperspectral image (HSI) classification has adopted deep neural networks (DNNs) and shown remarkable performances, there is a lack of studies of the adversarial vulnerability for the HSI classifications.
Sungjune Park, Hong Joo Lee, Yong Man Ro
doaj +1 more source
Exploiting Doubly Adversarial Examples for Improving Adversarial Robustness
, 2022 Deep neural networks have shown outstanding performance in various areas, but adversarial examples can easily fool them. Although strong adversarial attacks have defeated diverse adversarial defense methods, adversarial training, which augments training ...
Cho, Seungju +3 more
core +1 more source