Results 71 to 80 of about 619 (184)

Strategic litigation as a challenge for deliberative democracy

American Journal of Political Science, EarlyView.
Abstract Strategic litigation is a growing public concern, but remains understudied in democratic theory. In strategic litigation, collectives go to court with a political agenda that goes beyond their specific case. How should we assess the legitimacy of strategic litigation? Building on Lafont's model of deliberative democracy and Klein's distinction
Svenja Ahlhaus
wiley   +1 more source

Visualizing Image Segmentation Network Behavior Through the Lens of Scale Space Analysis

Computer Graphics Forum, EarlyView.
Abstract Deep neural networks are widely used for image segmentation, also in sensitive applications such as medical imaging or autonomous driving. However, few explainable AI methods are available that help developers understand such networks beyond classification.
A. C. Mikliss, T. Schultz
wiley   +1 more source

On the Feasibility and Generality of Patch-Based Adversarial Attacks on Semantic Segmentation Problems

, 2022
Deep neural networks were applied with success in a myriad of applications, but in safety critical use cases adversarial attacks still pose a significant threat. These attacks were demonstrated on various classification and detection tasks and are usually considered general in a sense that arbitrary network outputs can be generated by them.
Soma Kontár, András Horváth
openaire   +2 more sources

ADVERSARIAL PATCH DETECTION METHOD VIA MATHEMATICAL TRANSFORMATIONS

Безопасность информационных технологий
The widespread deployment of artificial intelligence technologies is motivated by their demonstrated effectiveness in applied domains, notably in image processing.
Dmitry A. Yesipov, Alyona D. Kletenkova, Ilya Yu. Popov   +2 more
doaj   +1 more source

SPINE: VAE‐driven Counterfactuals for Decision Boundary Maps

Computer Graphics Forum, EarlyView.
Abstract As Deep Learning models become increasingly complex, Explainable AI becomes essential for deploying machine learning classifiers. Decision Boundary Mapping (DBM) is a technique for visualizing a classifier's global decision boundary. Despite their relative success, current DBM methods rely on global inverse multidimensional projections that ...
I.M. Bloemen, V. Prasad, F. V. Paulovich
wiley   +1 more source

Textile and colour defect detection using deep learning methods

Coloration Technology, EarlyView.
Abstract Recent advances in deep learning (DL) have significantly enhanced the detection of textile and colour defects. This review focuses specifically on the application of DL‐based methods for defect detection in textile and coloration processes, with an emphasis on object detection and related computer vision (CV) tasks.
Hao Cui, Abdel‐Fattah Seyam, Renzo Shamey   +2 more
wiley   +1 more source

Concept-Based Masking: A Patch-Agnostic Defense Against Adversarial Patch Attacks

CoRR
neurips ...
Ayushi Mehrotra, Derek Peng, Dipkamal Bhusal, Nidhi Rastogi   +3 more
openaire   +2 more sources

Recruitment in Times of Crisis: The Impact of Negative Signals and CSR on Job Seekers' Attraction to Multinational Enterprises

Journal of Management Studies, EarlyView.
Abstract Recruitment research has traditionally focused on how positive signals about organizations influence job seekers' perceptions and attraction to them, despite the fact that job seekers often encounter a mix of positive and negative information about prospective employers.
Keyan Lai, Kristina Potočnik
wiley   +1 more source

Effective faking of verbal deception detection with target‐aligned adversarial attacks

Legal and Criminological Psychology, EarlyView.
Abstract Background Deception detection through analysing language is a promising avenue using both human judgements and automated machine learning judgements. For both forms of credibility assessment, automated adversarial attacks that rewrite deceptive statements to appear truthful pose a serious threat.
Bennett Kleinberg, Riccardo Loconte, Bruno Verschuere   +2 more
wiley   +1 more source

BB-Patch: BlackBox Adversarial Patch-Attack using Zeroth-Order Optimization

CoRR
Deep Learning has become popular due to its vast applications in almost all domains. However, models trained using deep learning are prone to failure for adversarial samples and carry a considerable risk in sensitive applications. Most of these adversarial attack strategies assume that the adversary has access to the training data, the model parameters,
Satyadwyoom Kumar, Saurabh Gupta 0007, Arun Balaji Buduru   +2 more
openaire   +2 more sources