Y
Yong Jiang
Researcher at Tsinghua University
Publications - 10
Citations - 106
Yong Jiang is an academic researcher from Tsinghua University. The author has contributed to research in topics: Deep learning & Information privacy. The author has an hindex of 4, co-authored 10 publications receiving 34 citations.
Papers
More filters
Posted Content
Backdoor Attack against Speaker Verification
TL;DR: This paper demonstrates that it is possible to inject the hidden backdoor for infecting speaker verification models by poisoning the training data and designs a clustering-based attack scheme where poisoned samples from different clusters will contain different triggers, based on the understanding of verification tasks.
Proceedings ArticleDOI
Backdoor Attack Against Speaker Verification
TL;DR: Zhang et al. as discussed by the authors demonstrate that it is possible to inject the hidden backdoor for infecting speaker verification models by poisoning the training data, where poisoned samples from different clusters will contain different triggers (i.e., pre-defined utterances), based on their understanding of verification tasks.
Proceedings ArticleDOI
Adversarial Defense Via Local Flatness Regularization
TL;DR: This paper defines the local flatness of the loss surface as the maximum value of the chosen norm of the gradient regarding to the input within a neighborhood centered on the benign sample, and discusses the relationship between the localflatness and adversarial vulnerability.
Posted Content
Visual Privacy Protection via Mapping Distortion
TL;DR: In the modified dataset generated by MDP, the image and its label are not consistent, whereas the DNNs trained on it can still achieve good performance on benign testing set, and this method can protect privacy when the dataset is leaked.
Proceedings Article
Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search
TL;DR: CSE-Autoloss as discussed by the authors proposes an effective convergence-simulation driven evolutionary search algorithm, which can accelerate the search progress by regularizing the mathematical rationality of loss candidates via two progressive convergence simulation modules: convergence property verification and model optimization simulation.