AI Frontier Lectures

Oct 29, 2025 · Artificial Intelligence

Why Early DI Attacks Outperform Modern Methods: A Systematic Study of Transferable Adversarial Images

This paper systematically evaluates 23 transferable adversarial attacks and 11 defenses on ImageNet, revealing that early DI attacks surpass newer methods when hyper‑parameters are fairly set, diffusion defenses offer false security, and higher transferability often reduces stealthiness, urging fair benchmarking and comprehensive metrics.