Results 101 to 110 of about 8,712 (199)

OD-SHIELD: Convolutional Autoencoder-Based Defense Against Adversarial Patch Attacks in Object Detection

IEEE Access
In the evolving landscape of deep neural network security, adversarial patch attacks present a serious challenge for object detection systems. We introduce OD-Shield, a novel defense approach that employs a convolutional autoencoder framework to detect ...
Byeongchan Kim, Heemin Kim, Minjung Kang, Hyunjee Nam, Sunghwan Park, Jaewoo Lee, Il-Youp Kwak   +6 more
doaj   +1 more source

High‐Fidelity Synthetic Data Replicates Clinical Prediction Performance in a Million‐Patient Diabetes Cohort

Advanced Science, Volume 13, Issue 29, 22 May 2026.
This study generates high‐fidelity synthetic longitudinal records for a million‐patient diabetes cohort, successfully replicating clinical predictive performance. However, deeper analysis reveals algorithmic biases and trajectory inconsistencies that escape standard quality metrics. These findings challenge current validation norms, demonstrating why a
Francisco Ortuño, Víctor M. de la Oliva Roque, Javier‐Ignacio Ramirez‐Lopez, David P. Kreil, Joaquín Dopazo, Carlos Loucera   +5 more
wiley   +1 more source

Patch is enough: naturalistic adversarial patch against vision-language pre-training models

Visual Intelligence
Visual language pre-training (VLP) models have demonstrated significant success in various domains, but they remain vulnerable to adversarial attacks. Addressing these adversarial vulnerabilities is crucial for enhancing security in multi-modal learning.
Dehong Kong, Siyuan Liang, Xiaopeng Zhu, Yuansheng Zhong, Wenqi Ren   +4 more
doaj   +1 more source

Scalable One-Pixel Attacks on Deep Neural Networks for High-Resolution Images

Mathematics
Recent studies have shown that deep neural networks can be misled by adversarial examples that involve only imperceptible perturbations. Among these, one-pixel attacks (OPA) represent an extreme yet powerful threat, as they alter only a single pixel of ...
Wonhong Nam, Hyunwoo Moon, Kunha Kim, Hyunyoung Kil   +3 more
doaj   +1 more source

Adaptive Q‐Wavelet Transform and Kalman Filtering for Power Quality Disturbance Prediction and Carbon Emission Impact Analysis in Smart Grids

Engineering Reports, Volume 8, Issue 5, May 2026.
Maintaining power quality (PQ) and minimizing carbon emissions are crucial for sustainable smart grids, especially with increasing renewable energy integration. This paper proposes a novel method combining Adaptive Q‐Wavelet Transform (AQWT) and Kalman Filtering (KF) to predict PQ disturbances and faults while analyzing their impact on carbon emissions.
Abhishek Raj, Anvesha Nandi, Sunil Kumar Sawant, Anil Kumar Swain, Ashlok Prasad Yadav, Ajaya kumar parida, Mohamed Metwally Mahmoud, Vojtech Blazek, Daniel Eutyche Mbadjoun Wapet, Shazly Nasser Fahmy   +9 more
wiley   +1 more source

Perceptual Carlini-Wagner Attack: A Robust and Imperceptible Adversarial Attack Using LPIPS

IEEE Access
Adversarial attacks on deep neural networks (DNNs) present significant challenges by exploiting model vulnerabilities using perturbations that are often imperceptible to human observers.
Liming Fan, Anis Salwa Mohd Khairuddin, Haichuan Liu, Khairunnisa Binti Hasikin   +3 more
doaj   +1 more source

Why Autonomous Vehicles Are Not Ready Yet: A Multi‐Disciplinary Review of Problems, Attempted Solutions, and Future Directions

Journal of Field Robotics, Volume 43, Issue 3, Page 2254-2341, May 2026.
ABSTRACT Personal autonomous vehicles can sense their surrounding environment, plan their route, and drive with little or no involvement of human drivers. Despite the latest technological advancements and the hopeful announcements made by leading entrepreneurs, to date no personal vehicle is approved for road circulation in a “fully” or “semi ...
Xingshuai Dong, Massimiliano Cappuccio, Fady Alnajjar, Luqman Ali, Hamad Al Jassmi, Essam Debie, Milad Ghasrikhouzani, Alessandro Lanteri, Tate McGregor, Oleksandra Molloy, Alice Plebe, Michael Regan, Eduardo Sandoval, Dongmo Zhang   +13 more
wiley   +1 more source

How to grow new applications out of old research? Evidence from firm cumulative investments in deep learning

Strategic Management Journal, Volume 47, Issue 5, Page 1333-1367, May 2026.
Abstract Research Summary Firm technological research has the potential to spawn multiple applications. Despite recognizing such potential, past literature disagrees on the process through which firms discover and grow new applications out of their past technological research.
Xirong (Subrina) Shen
wiley   +1 more source

Rethinking adversarial attacks on neuromorphic models

Neuromorphic Computing and Engineering
Spiking neural networks (SNN) are biologically inspired artificial neural networks that emulate the behaviour of biological neurons in spiking-based computational units.
Soukaina Aji, Pierre Boulet, Mohamed Bouassida, Ihsen Alouani   +3 more
doaj   +1 more source

A comparative study of phantom sponge for monocular 3D object detection on edge devices

ICT Express
In this paper, we expand the Phantom Sponge attack to monocular 3D object detection to increase false positives and detection times, thereby impairing the performance of edge devices.
Shaheer Siddiqui, Jinpyung Kim, Jangho Lee   +2 more
doaj   +1 more source