2 citations · 3 across the 8 of their papers we have counts for
6 papers · 1 filter
When Trees Are Not Enough: Learning Mixed-Topology Feature Graphs with Adaptive Graph Sparse Autoencoders
Xiaozuo Shen, Yifei Cai, Tian Tan +3
Sparse autoencoders (SAEs) expose interpretable features in large language model activations, yet existing structured SAEs impose single-parent trees or forests, while post-hoc gra…
DegreeSpar: Structured Degree Sparsity for Efficient Secure Transformer Inference
Yifei Cai, Zhuoran Li, Xiaozuo Shen +2
Secure Transformer inference protects sensitive inputs but incurs substantial cryptographic overhead, with nonlinear operations such as Softmax and GeLU becoming major bottlenecks.…
SecDTD: Dynamic Token Drop for Secure Transformers Inference
Yifei Cai, Zhuoran Li, Yizhou Feng +4
The rapid adoption of Transformer-based AI has been driven by accessible models such as ChatGPT, which provide API-based services for developers and businesses. However, as these o…
DF-LoGiT: Data-Free Logic-Gated Backdoor Attacks in Vision Transformers
Xiaozuo Shen, Yifei Cai, Rui Ning +2
The widespread adoption of Vision Transformers (ViTs) elevates supply-chain risk on third-party model hubs, where an adversary can implant backdoors into released checkpoints. Exis…
RPP: A Certified Poisoned-Sample Detection Framework for Backdoor Attacks under Dataset Imbalance
Miao Lin, Feng Yu, Rui Ning +6
Deep neural networks are highly susceptible to backdoor attacks, yet most defense methods to date rely on balanced data, overlooking the pervasive class imbalance in real-world sce…
Towards Zero Rotation and Beyond: Architecting Neural Networks for Fast Secure Inference with Homomorphic Encryption
Yifei Cai, Yizhou Feng, Qiao Zhang +2
Privacy-preserving deep learning addresses privacy concerns in Machine Learning as a Service (MLaaS) by using Homomorphic Encryption (HE) for linear computations. However, the comp…