4 papers
Everywhere Attack: Attacking Locally and Globally to Boost Targeted Transferability
Hui Zeng, Sanshuai Cui, Biwei Chen +1
Adversarial examples' (AE) transferability refers to the phenomenon that AEs crafted with one surrogate model can also fool other models. Notwithstanding remarkable progress in unt…
Two Heads Are Better Than One: Averaging along Fine-Tuning to Improve Targeted Transferability
Hui Zeng, Sanshuai Cui, Biwei Chen +1
With much longer optimization time than that of untargeted attacks notwithstanding, the transferability of targeted attacks is still far from satisfactory. Recent studies reveal th…
Enhancing targeted transferability via feature space fine-tuning
Hui Zeng, Biwei Chen, Anjie Peng
Adversarial examples (AEs) have been extensively studied due to their potential for privacy protection and inspiring robust neural networks. Yet, making a targeted AE transferable…
A comparison study of CNN denoisers on PRNU extraction
Hui Zeng, Morteza Darvish Morshedi Hosseini, Kang Deng +2
Performance of the sensor-based camera identification (SCI) method heavily relies on the denoising filter in estimating Photo-Response Non-Uniformity (PRNU). Given various attempts…