Results 31 to 40 of about 85,147 (260)
Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial Robustness
, 2022 Accepted by ECCV 2022 oral ...
Zhang, Chaoning +6 more
openaire +2 more sources
IEEE Open Journal of Control Systems, 2022 In this work, we propose a framework in which we use a Lipschitz-constrained loss minimization scheme to learn feedback control policies with guarantees on closed-loop stability, adversarial robustness, and generalization.
Abed AlRahman Al Makdah +2 more
doaj +1 more source
, 2019 The prediction accuracy has been the long-lasting and sole standard for comparing the performance of different image classification models, including the ImageNet competition.
Su, Dong +5 more
core +1 more source
Adversarial Robustness: Softmax versus Openmax
, 2017 Deep neural networks (DNNs) provide state-of-the-art results on various tasks and are widely used in real world applications. However, it was discovered that machine learning models, including the best performing DNNs, suffer from a fundamental problem ...
Boult, Terrance E. +2 more
core +1 more source
A Comparative Study on the Performance and Security Evaluation of Spiking Neural Networks
IEEE Access, 2022 The brain-inspired Spiking neural networks (SNN) claim to present advantages for visual classification tasks in terms of energy efficiency and inherent robustness.
Yanjie Li +3 more
doaj +1 more source
Analysis of classifiers' robustness to adversarial perturbations
, 2016 The goal of this paper is to analyze an intriguing phenomenon recently discovered in deep networks, namely their instability to adversarial perturbations (Szegedy et. al., 2014).
Fawzi, Alhussein +2 more
core +1 more source
Meniscus Pixel Printing for Contact‐Lens Vision Sensing and Robotic Control
Advanced Functional Materials, EarlyView.A visual‐sensing contact lens is enabled by meniscus pixel printing (MPP), which rapidly patterns a 200 µm perovskite photodetector pixel in 1 s without masks, vacuum processing, or bulky equipment. A deep‐learning‐based super‐resolution reconstructs sparse on‐lens signals into 80 × 80 high‐resolution visual information, while AI‐driven eye‐tracking ...
Byung‐Hoon Gong +7 more
wiley +1 more source
Understanding the Energy vs. Adversarial Robustness Trade-Off in Deep Neural Networks
IEEE Open Journal of Circuits and Systems, 2021 Adversarial examples, which are crafted by adding small perturbations to typical inputs in order to fool the prediction of a deep neural network (DNN), pose a threat to security-critical applications, and robustness against adversarial examples is ...
Kyungmi Lee, Anantha P. Chandrakasan
doaj +1 more source
Exploring Robust Features for Improving Adversarial Robustness
IEEE Transactions on CyberneticsWhile deep neural networks (DNNs) have revolutionized many fields, their fragility to carefully designed adversarial attacks impedes the usage of DNNs in safety-critical applications. In this paper, we strive to explore the robust features which are not affected by the adversarial perturbations, i.e., invariant to the clean image and its adversarial ...
Hong Wang +3 more
openaire +3 more sources
Computational Modeling Meets 3D Bioprinting: Emerging Synergies in Cardiovascular Disease Modeling
Advanced Healthcare Materials, EarlyView.Emerging advances in three‐dimensional bioprinting and computational modeling are reshaping cardiovascular (CV) research by enabling more realistic, patient‐specific tissue platforms. This review surveys cutting‐edge approaches that merge biomimetic CV constructs with computational simulations to overcome the limitations of traditional models, improve ...
Tanmay Mukherjee +7 more
wiley +1 more source