4 papers
Kill Two Birds with One Stone! Trajectory enabled Unified Online Detection of Adversarial Examples and Backdoor Attacks
Anmin Fu, Fanyu Meng, Huaibing Peng +5
The proposed UniGuard is the first unified online detection framework capable of simultaneously addressing adversarial examples and backdoor attacks. UniGuard builds upon two key i…
Reversible Data Hiding over Encrypted Images via Intrinsic Correlation in Block-Based Secret Sharing
Jianhui Zou, Weijia Cao, Shuang Yi +2
With the rapid advancements in information technology, reversible data hiding over encrypted images (RDH-EI) has become essential for secure image management in cloud services. How…
Camel: Communication-Efficient and Maliciously Secure Federated Learning in the Shuffle Model of Differential Privacy
Shuangqing Xu, Yifeng Zheng, Zhongyun Hua
Federated learning (FL) has rapidly become a compelling paradigm that enables multiple clients to jointly train a model by sharing only gradient updates for aggregation, without re…
M-to-N Backdoor Paradigm: A Multi-Trigger and Multi-Target Attack to Deep Learning Models
Linshan Hou, Zhongyun Hua, Yuhong Li +2
Deep neural networks (DNNs) are vulnerable to backdoor attacks, where a backdoored model behaves normally with clean inputs but exhibits attacker-specified behaviors upon the input…