Opinion

IBM's AI agent Bob easily duped to run malware, researchers show

That's apparently the case with Bob. IBM's documentation, the PromptArmor Threat Intelligence Team explained in a writeup provided to The Register, includes a warning that setting high-risk commands ...

Are Copilot prompt injection flaws vulnerabilities or AI limits?

Microsoft has pushed back against claims that multiple prompt injection and sandbox-related issues raised by a security ...
IEEE

Texture- and Shape-Based Adversarial Attacks for Overhead Image Vehicle Detection

Abstract: Detecting vehicles in aerial images is difficult due to complex backgrounds, small object sizes, shadows, and occlusions. Although recent deep learning advancements have improved object ...
IEEE

STEAM: Style Transfer Enabled Adversarial Attack With Attention Mechanism on Remote Sensing Image Scene Classification

Abstract: Research on adversarial attacks in remote sensing tasks have predominantly focused on designing perturbations or patches, presenting challenges in balancing attack success rate and ...