Results 111 to 120 of about 1,662,189 (295)
Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples
With the evolution of self-supervised learning, the pre-training paradigm has emerged as a predominant solution within the deep learning landscape.
Wan, W +9 more
core +1 more source
Downstream-agnostic Adversarial Examples [PDF]
, 2023 Self-supervised learning usually uses a large amount of unlabeled data to pre-train an encoder which can be used as a general-purpose feature extractor, such that downstream users only need to perform fine-tuning operations to enjoy the benefit of "large
Zhou, Ziqi +6 more
core +1 more source
Advanced Science, EarlyView.KFO‐Atlas reveals how real‐world aromas are organized as structured mixtures rather than individual molecules. Building on these principles, KFO‐Gen, a generative AI framework, designs perceptually valid aroma formulations and reconstructs meat‐like aromas exclusively from plant‐derived odorants, providing a foundation for mixture‐level studies and AI ...
Jingzhi Zhang +5 more
wiley +1 more source
Advanced Science, EarlyView.Recent advances in metasurface‐enabled low‐observable technologies are reviewed from the perspective of cross‐scale material–structure synergy. Electromagnetic, thermal, optical, and acoustic stealth are highlighted together with dynamic tuning, programmable coding, data‐driven inverse design, artificial intelligence, multispectral compatibility, and ...
Shuhao Wang +5 more
wiley +1 more source
Q‐LEAP: Millisecond Hyperdimensional Optimization for Full‐Spectrum Optical Metamaterials
Advanced Science, EarlyView.Q‐LEAP integrates physics‐informed residual machine learning with factorization‐machine‐encoded quantum annealing to design full‐spectrum optical metamaterials. It explores a 2108 design space and, in a single 2.56 ms annealing step, reaches 85.83% of the theoretical FoM limit, enabling selective 5‐8 µm emission with 3–5 and 8–14 µm suppression and ∼40×
Zikang Guo +3 more
wiley +1 more source
Exploring Adversarial Examples
, 2018 Failure cases of black-box deep learning, e.g. adversarial examples, might have severe consequences in healthcare. Yet such failures are mostly studied in the context of real-world images with calibrated attacks.
Anirban Mukhopadhyay +7 more
core +1 more source
Intriguing Properties of Adversarial Examples
CoRR, 2017 17 ...
Ekin Dogus Cubuk +3 more
openaire +4 more sources
Adversarial Examples for CNN-Based Malware Detectors
IEEE Access, 2019 The convolutional neural network (CNN)-based models have achieved tremendous breakthroughs in many end-to-end applications, such as image identification, text classification, and speech recognition.
Bingcai Chen +4 more
doaj +1 more source
Advanced Electronic Materials, EarlyView.A physics‐guided generative surrogate framework is developed for programmable metasurface beamforming. Mode‐conditioned binary state generation, aperture‐physics prediction, routed residual correction, NSGA‐II optimization, and CST validation are combined to support fast candidate screening and full‐wave beam refinement across single‐beam, dual‐beam ...
Wenqian Liu +4 more
wiley +1 more source
Advanced Energy Materials, EarlyView.Machine learning interatomic potentials bridge quantum accuracy and computational efficiency for materials discovery. Architectures from Gaussian process regression to equivariant graph neural networks, training strategies including active learning and foundation models, and applications in solid‐state electrolytes, batteries, electrocatalysts ...
In Kee Park +19 more
wiley +1 more source