Results 21 to 30 of about 25,829 (292)
Increasing the Robustness of Image Quality Assessment Models Through Adversarial Training
TechnologiesThe adversarial robustness of image quality assessment (IQA) models to adversarial attacks is emerging as a critical issue. Adversarial training has been widely used to improve the robustness of neural networks to adversarial attacks, but little in-depth
Anna Chistyakova +6 more
doaj +3 more sources
Assessing the adversarial robustness of multimodal medical AI systems: insights into vulnerabilities and modality interactions [PDF]
Frontiers in MedicineThe emergence of both task-specific single-modality models and general-purpose multimodal large models presents new opportunities, but also introduces challenges, particularly regarding adversarial attacks.
Ekaterina Mozhegova +5 more
doaj +2 more sources
On Saliency Maps and Adversarial Robustness [PDF]
, 2021 A Very recent trend has emerged to couple the notion of interpretability and adversarial robustness, unlike earlier efforts which solely focused on good interpretations or robustness against adversaries. Works have shown that adversarially trained models exhibit more interpretable saliency maps than their non-robust counterparts, and that this behavior
Puneet Mangla +2 more
openaire +4 more sources
Exploring Adversarial Robustness of LiDAR Semantic Segmentation in Autonomous Driving. [PDF]
Sensors (Basel), 2023 Deep learning networks have demonstrated outstanding performance in 2D and 3D vision tasks. However, recent research demonstrated that these networks result in failures when imperceptible perturbations are added to the input known as adversarial attacks.
Mahima KTY +3 more
europepmc +2 more sources
On the Adversarial Robustness of Vision Transformers
Trans. Mach. Learn. Res., 2021 Following the success in advancing natural language processing and understanding, transformers are expected to bring revolutionary changes to computer vision. This work provides a comprehensive study on the robustness of vision transformers (ViTs) against adversarial perturbations.
Rulin Shao +4 more
openaire +4 more sources
Understanding adversarial robustness against on-manifold adversarial examples
Pattern RecognitionDeep neural networks (DNNs) are shown to be vulnerable to adversarial examples. A well-trained model can be easily attacked by adding small perturbations to the original data. One of the hypotheses of the existence of the adversarial examples is the off-manifold assumption: adversarial examples lie off the data manifold. However, recent research showed
Yanbo Fan, Zhi-Quan Luo
exaly +3 more sources
Residual-guided hybrid framework for adversarially robust deep learning-based network intrusion detection. [PDF]
PLoS ONEThe growing sophistication of cyber threats and adversarial attacks poses critical challenges to the security and robustness of machine learning models deployed in real-world systems.
Sudip Saha +4 more
doaj +2 more sources
On the Adversarial Robustness of Robust Estimators [PDF]
IEEE Transactions on Information Theory, 2020 Motivated by recent data analytics applications, we study the adversarial robustness of robust estimators. Instead of assuming that only a fraction of the data points are outliers as considered in the classic robust estimation setup, in this paper, we consider an adversarial setup in which an attacker can observe the whole dataset and can modify all ...
Lifeng Lai, Erhan Bayraktar
openaire +2 more sources
Recent Advances in Adversarial Training for Adversarial Robustness [PDF]
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, 2021 Adversarial training is one of the most effective approaches for deep learning models to defend against adversarial examples. Unlike other defense strategies, adversarial training aims to enhance the robustness of models intrinsically. During the past few years, adversarial training has been studied and discussed from various aspects, which deserves ...
Tao Bai +4 more
openaire +2 more sources
The Adversarial Robustness of Sampling [PDF]
Proceedings of the 39th ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems, 2020 Random sampling is a fundamental primitive in modern algorithms, statistics, and machine learning, used as a generic method to obtain a small yet "representative" subset of the data. In this work, we investigate the robustness of sampling against adaptive adversarial attacks in a streaming setting: An adversary sends a stream of elements from a ...
Omri Ben-Eliezer, Eylon Yogev
openaire +3 more sources