Tag: adversarial attacks
Browse our exclusive articles!
Prevent Image Analysis by MLLMs Using Visual Prompt Injection
Protect your images from multi-modal large language models with ImageProtector, a new method that blocks unauthorized AI image analysis.
Exploiting Denoising Flaws in Diffusion Language Models
Discover how denoising irreversibility exposes vulnerabilities in diffusion language models and explore strategies to enhance AI safety and robustness.
BadImplant: Multi-Targeted Injection Backdoor Attack on GNNs
Discover BadImplant, a novel injection-based multi-targeted backdoor attack on graph neural networks that preserves graph integrity and evades defenses.
CAAP: Advanced Adversarial Patch Attacks on Palmprint AI
Discover CAAP, a novel adversarial patch framework disrupting palmprint recognition systems under real-world capture conditions.
Physical Adversarial Attacks on AI Surveillance Systems
Explore physical adversarial attacks on AI surveillance, focusing on detection, tracking, and visible-infrared evasion techniques in real-world scenarios.