AI Models Are Starting to Learn by Asking Themselves Questions

An AI model that learns without human input—by posing interesting queries for itself—might point the way to superintelligence ...
IEEE

Secure Load Frequency Control of Cyber–Physical Power Systems Under Cyber Attacks and Delays

Abstract: This article proposes a secure load frequency control (LFC) method for cyber–physical power systems integrated with photovoltaic energy and electric vehicle, addressing the challenges of ...
IEEE

Adversarial Examples Detection With Enhanced Image Difference Features Based on Local Histogram Equalization

Abstract: Deep Neural Networks (DNNs) have recently made significant strides in various fields; however, they are susceptible to adversarial examples—crafted inputs with imperceptible perturbations ...
GitHub

TransferAttack is a pytorch framework to boost the adversarial transferability for image classification.

Devling into Adversarial Transferability on Image Classification: A Review, Benchmark and Evaluation will be released soon. We also release a list of papers about transfer-based attacks here. We adopt ...