activity
20122022
most citedImperceptible Backdoor Attack: From Input Space to Feature Representation

7 citations · 35 across the 16 of their papers we have counts for

collaborators

18 papers

eess.IV2022

Learning to Immunize Images for Tamper Localization and Self-Recovery

Qichao Ying, Hang Zhou, Zhenxing Qian +2

Digital images are vulnerable to nefarious tampering attacks such as content addition or removal that severely alter the original meaning. It is somehow like a person without prote…

cs.CR20224 cited

Hiding Images in Deep Probabilistic Models

Haoyu Chen, Linqi Song, Zhenxing Qian +2

Data hiding with deep neural networks (DNNs) has experienced impressive successes in recent years. A prevailing scheme is to train an autoencoder, consisting of an encoding network…

cs.CV20221 cited

Generative Model Watermarking Based on Human Visual System

Li Zhang, Yong Liu, Shaoteng Liu +4

Intellectual property protection of deep neural networks is receiving attention from more and more researchers, and the latest research applies model watermarking to generative mod…

cs.CV20226 cited

Multimodal Fake News Detection via CLIP-Guided Learning

Yangming Zhou, Qichao Ying, Zhenxing Qian +2

Multimodal fake news detection has attracted many research interests in social forensics. Many existing approaches introduce tailored attention mechanisms to guide the fusion of un…

cs.CR20221 cited

Deniable Steganography

Yong Xu, Zhihua Xia, Zichi Wang +2

Steganography conceals the secret message into the cover media, generating a stego media which can be transmitted on public channels without drawing suspicion. As its countermeasur…

cs.CR20227 cited

Imperceptible Backdoor Attack: From Input Space to Feature Representation

Nan Zhong, Zhenxing Qian, Xinpeng Zhang

Backdoor attacks are rapidly emerging threats to deep neural networks (DNNs). In the backdoor attack scenario, attackers usually implant the backdoor into the target model by manip…