8 papers
Shared Vulnerabilities in Robustness-Optimized Defenses: One Breach Exposes the Family
Hanrui Wang, Ruihao Zheng, Shuo Wang +3
Adversarial robustness optimization aims to preserve correct prediction under adversarial perturbations, and has produced substantial robustness gains through methods such as adver…
On the Role of Artificial Intelligence in Human-Machine Symbiosis
Ching-Chun Chang, Yuchen Guo, Hanrui Wang +2
The evolution of artificial intelligence (AI) has rendered the boundary between humanity and computational machinery increasingly ambiguous. In the presence of more interwoven rela…
DiffMI: Breaking Face Recognition Privacy via Diffusion-Driven Training-Free Model Inversion
Hanrui Wang, Shuo Wang, Chun-Shien Lu +1
Face recognition poses serious privacy risks due to its reliance on sensitive and immutable biometric data. While modern systems mitigate privacy risks by mapping facial images to…
Imitation Game for Adversarial Disillusion with Chain-of-Thought Reasoning in Generative AI
Ching-Chun Chang, Fan-Yun Chen, Shih-Hong Gu +3
As the cornerstone of artificial intelligence, machine perception confronts a fundamental threat posed by adversarial illusions. These adversarial attacks manifest in two primary f…
Minimal Cascade Gradient Smoothing for Fast Transferable Preemptive Adversarial Defense
Hanrui Wang, Ching-Chun Chang, Chun-Shien Lu +3
Adversarial attacks persist as a major challenge in deep learning. While training- and test-time defenses are well-studied, they often reduce clean accuracy, incur high cost, or fa…
GreedyPixel: Fine-Grained Black-Box Adversarial Attack Via Greedy Algorithm
Hanrui Wang, Ching-Chun Chang, Chun-Shien Lu +2
Deep neural networks are highly vulnerable to adversarial examples, which are inputs with small, carefully crafted perturbations that cause misclassification -- making adversarial…