Results 101 to 110 of about 804,777 (293)

On Adaptive Attacks to Adversarial Example Defenses

CoRR, 2020
Adaptive attacks have (rightfully) become the de facto standard for evaluating defenses to adversarial examples. We find, however, that typical adaptive evaluations are incomplete. We demonstrate that thirteen defenses recently published at ICLR, ICML and NeurIPS---and chosen for illustrative and pedagogical purposes---can be circumvented despite ...
Florian Tramèr, Nicholas Carlini, Wieland Brendel, Aleksander Madry   +3 more
openaire   +3 more sources

Artificial intelligence and liquidation: Reality, destiny and fantasy

International Insolvency Review, EarlyView.
Abstract Artificial intelligence (AI) is increasingly reshaping the administration of corporate liquidation. Beyond its established role in financial prediction and data analytics, AI is now assisting insolvency practitioners in identifying the onset of financial distress, managing creditor communications, tracing and valuing assets and enhancing ...
Kai Zhang, Jingchen Zhao
wiley   +1 more source

DISCO: Adversarial Defense with Local Implicit Functions [PDF]

, 2022
The problem of adversarial defenses for image classification, where the goal is to robustify a classifier against adversarial examples, is considered.
Vasconcelos, Nuno, Ho, Chih-Hui
core   +1 more source

"Defense Expenditures and Allied Cooperation" [PDF]

This paper investigates the implications of cooperative and non-cooperative defense spending of allied countries in conflicting blocs using static and leader-follower game models.
Toshihiro Ihori
core  

Human biomarker navigator

iMeta, EarlyView.
The Human Biomarker Navigator integrates the disease continuum, biomarker dynamics, cross‐organ biomarker networks, biomarker classification, and technology‐driven paradigms. It maps how biomarkers link multi‐system physiology and pathology across the nervous, respiratory, endocrine, circulatory, immune, digestive, urinary, reproductive, and ...
Meng‐Yao Li, Qian Zhang, Zijie Wang, Zeping Gui, Jing Liu, Jingda Li, Maojun Jiang, Zukang Chang, Qingqing Han, Bendong Yang, Tariq Saeed, Jun Li, Jinghan Jia, Chenghu Song, Tong Shao, Tianhuan Peng, Xueying Zhang, Pingping Guo, Jun Luo, Gangao Yang, Yuan Wan, Gokhan Zengin, Quan Yuan, Lingru Li, Xiaohui Fan, Yang Luo, Lvyun Zhu, Yanfei Zheng, Wenjun Mao, Wenlong Sun   +29 more
wiley   +1 more source

A knowledge distillation strategy for enhancing the adversarial robustness of lightweight automatic modulation classification models

IET Communications
Automatic modulation classification models based on deep learning models are at risk of being interfered by adversarial attacks. In an adversarial attack, the attacker causes the classification model to misclassify the received signal by adding carefully
Fanghao Xu, Chao Wang, Jiakai Liang, Chenyang Zuo, Keqiang Yue, Wenjun Li   +5 more
doaj   +1 more source

Symmetry Defense Against CNN Adversarial Perturbation Attacks [PDF]

, 2023
This paper uses symmetry to make Convolutional Neural Network classifiers (CNNs) robust against adversarial perturbation attacks. Such attacks add perturbation to original images to generate adversarial images that fool classifiers such as road sign ...
Lindqvist, Blerta
core   +1 more source

Preparing for Tomorrow's Teamwork: Insights From eSports on How Human Expertise Shapes Training Needs for AI‐Integrated Work

Journal of Organizational Behavior, EarlyView.
ABSTRACT As organizations increasingly adopt human‐AI teams (HATs), understanding how to enhance team performance is paramount. A crucially underexplored area for supporting HATs is training, particularly helping human teammates to work with these inorganic counterparts.
Caitlin M. Lancaster, Christopher Flathmann, Jennifer Hsu, Nathan J. McNeese, Thomas A. O'Neill, Eduardo Salas   +5 more
wiley   +1 more source

PuVAE: A Variational Autoencoder to Purify Adversarial Examples

IEEE Access, 2019
Deep neural networks are widely used and exhibit excellent performance in many areas. However, they are vulnerable to adversarial attacks that compromise networks at inference time by applying elaborately designed perturbations to input data.
Uiwon Hwang, Jaewoo Park, Hyemi Jang, Sungroh Yoon, Nam Ik Cho   +4 more
doaj   +1 more source

MAFFN-SAT: 3-D Point Cloud Defense via Multiview Adaptive Feature Fusion and Smooth Adversarial Training

Adversarial attacks pose a significant threat to deep neural networks (DNNs) used for 3-D point cloud classification, especially in safety-critical applications.
Gao, Y, Pang, S, Zhang, S, Du, A, Zhang, J   +4 more
core   +1 more source