Results 121 to 130 of about 17,780 (281)
195208Adversarial attacks pose a significant threat to the reliability and trustworthiness of machine learning systems, particularly in image classification tasks like deepfake detection.
Bunzel, Niklas +4 more
core +1 more source
A Systems‐Level Approach to Address Risks and Ethics in Artificial Intelligence Systems
Systems Engineering, EarlyView.ABSTRACT Artificial intelligence (AI) is rapidly changing the world, from completely controlling routine or mundane tasks like text and image generation, to powering advanced algorithms that control critical systems. The recent advances in generative AI quickly overwhelmed multiple industries from education to finance as first adopters rushed (and ...
Vincent P. Paglioni, Torrey Mortenson
wiley +1 more source
Exploiting Machine Learning to Subvert Your Spam Filter
, 2008 Using statistical machine learning for making security decisions introduces new vulnerabilities in large scale systems. This paper shows how an adversary can exploit statistical machine learning, as used in the SpamBayes spam filter, to render it useless—
Nelson, Blaine +8 more
core
World Journal of Otorhinolaryngology - Head and Neck Surgery, EarlyView.ABSTRACT Objective To provide a comprehensive review of the current landscape of artificial intelligence (AI) applications in voice disorder, with emphasis on emerging applications, limitations, and future directions for clinical integration. Methods Literature review.
Rachel B. Kutler, Anaïs Rameau
wiley +1 more source
DrLS: Distortion‐Resistant Lossless Steganography via Colour Depth Interpolation
CAAI Transactions on Intelligence Technology, EarlyView.ABSTRACT The lossless data steganography is to hide a certain amount of information into a container image. Previous lossless steganography methods fail to strike a balance between capacity, imperceptibility, accuracy, and robustness, commonly vulnerable to distortion on container images.
Youmin Xu +3 more
wiley +1 more source
Informatika, 2019 This paper addresses the problem of dependence of the success rate of adversarial attacks to the deep neural networks on the biomedical image type and control parameters of generation of adversarial examples.
D. M. Voynov, V. A. Kovalev
doaj
CAAI Transactions on Intelligence Technology, EarlyView.ABSTRACT Accurate surface‐pressure prediction over broad operating envelopes is critical for supersonic aerodynamic analysis and design. To overcome the bottlenecks of traditional computational fluid dynamics (CFD) in real‐time performance and computational efficiency, data‐driven deep learning methods have emerged. However, existing data‐driven models
Hongbin Xu, Yin Long, Junlin Wu
wiley +1 more source
Enhancing Adversarial Defense via Brain Activity Integration Without Adversarial Examples
SensorsAdversarial attacks on large-scale vision–language foundation models, such as the contrastive language–image pretraining (CLIP) model, can significantly degrade performance across various tasks by generating adversarial examples that are ...
Tasuku Nakajima +4 more
doaj +1 more source
ASTrA: Adversarial Self-supervised Training with Adaptive-Attacks
Existing self-supervised adversarial training (self-AT) methods rely on hand-crafted adversarial attack strategies for PGD attacks, which fail to adapt to the evolving learning dynamics of the model and do not account for instance-specific ...
Saini, Rajkumar +5 more
core
Application of Deep Learning in Virtual Power Plants—A Review
Energy Internet, EarlyView.ABSTRACT The advancement of deep learning (DL) has substantially improved the power grid’s ability to model and optimise diverse and highly complex tasks. Although intelligent transformation is an inevitable trend, traditional approaches increasingly reveal limitations in computational efficiency, nonlinear nonconvex optimisation, and multi‐layer ...
Hongjie Zhu +7 more
wiley +1 more source