58 citations · 147 across the 67 of their papers we have counts for
7 papers · 1 filter
New Challenges in Reinforcement Learning: A Survey of Security and Privacy
Yunjiao Lei, Dayong Ye, Sheng Shen +3
Reinforcement learning (RL) is one of the most important branches of AI. Due to its capacity for self-adaption and decision-making in dynamic environments, reinforcement learning h…
Momentum Gradient Descent Federated Learning with Local Differential Privacy
Mengde Han, Tianqing Zhu, Wanlei Zhou
Nowadays, the development of information technology is growing rapidly. In the big data era, the privacy of personal information has been more pronounced. The major challenge is to…
How Does a Deep Learning Model Architecture Impact Its Privacy? A Comprehensive Study of Privacy Attacks on CNNs and Transformers
Guangsheng Zhang, Bo Liu, Huan Tian +3
As a booming research area in the past decade, deep learning technologies have been driven by big data collected and processed on an unprecedented scale. However, privacy concerns…
Making DeepFakes more spurious: evading deep face forgery detection via trace removal attack
Chi Liu, Huajie Chen, Tianqing Zhu +2
DeepFakes are raising significant social concerns. Although various DeepFake detectors have been developed as forensic countermeasures, these detectors are still vulnerable to atta…
One Parameter Defense -- Defending against Data Inference Attacks via Differential Privacy
Dayong Ye, Sheng Shen, Tianqing Zhu +2
Machine learning models are vulnerable to data inference attacks, such as membership inference and model inversion attacks. In these types of breaches, an adversary attempts to inf…
Model Inversion Attack against Transfer Learning: Inverting a Model without Accessing It
Dayong Ye, Huiqiang Chen, Shuai Zhou +3
Transfer learning is an important approach that produces pre-trained teacher models which can be used to quickly build specialized student models. However, recent research on trans…
Label-only Model Inversion Attack: The Attack that Requires the Least Information
Dayong Ye, Tianqing Zhu, Shuai Zhou +2
In a model inversion attack, an adversary attempts to reconstruct the data records, used to train a target model, using only the model's output. In launching a contemporary model i…