2 citations · 6 across the 12 of their papers we have counts for
14 papers
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.…
HarmQ: Harmonic Backdoor Attacks Against Quantum Neural Networks
Junrui Zhang, Zemin Chen, Chunsheng Xin +2
Quantum Neural Networks (QNNs) have emerged as a promising paradigm for quantum machine learning in the Noisy Intermediate-Scale Quantum (NISQ) era, leveraging quantum phenomena su…
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…
PRIVEE: Privacy-Preserving Vertical Federated Learning Against Feature Inference Attacks
Sindhuja Madabushi, Haider Ali, Ahmad Faraz Khan +5
Vertical Federated Learning (VFL) enables collaborative model training across organizations that share common user samples but hold disjoint feature spaces. Despite its potential,…
Beam Profiling and Beamforming Modeling for mmWave NextG Networks
Efat Samir Fathalla, Sahar Zargarzadeh, Chunsheng Xin +5
This paper presents an experimental study on mmWave beam profiling on a mmWave testbed, and develops a machine learning model for beamforming based on the experiment data. The data…
Comet: A Communication-efficient and Performant Approximation for Private Transformer Inference
Xiangrui Xu, Qiao Zhang, Rui Ning +2
The prevalent use of Transformer-like models, exemplified by ChatGPT in modern language processing applications, underscores the critical need for enabling private inference essent…
Joint Linear and Nonlinear Computation across Functions for Efficient Privacy-Preserving Neural Network Inference
Qiao Zhang, Tao Xiang, Chunsheng Xin +2
While it is encouraging to witness the recent development in privacy-preserving Machine Learning as a Service (MLaaS), there still exists a significant performance gap for its depl…
DeepAuditor: Distributed Online Intrusion Detection System for IoT devices via Power Side-channel Auditing
Woosub Jung, Yizhou Feng, Sabbir Ahmed Khan +3
As the number of IoT devices has increased rapidly, IoT botnets have exploited the vulnerabilities of IoT devices. However, it is still challenging to detect the initial intrusion…
GALA: Greedy ComputAtion for Linear Algebra in Privacy-Preserved Neural Networks
Qiao Zhang, Chunsheng Xin, Hongyi Wu
Machine Learning as a Service (MLaaS) is enabling a wide range of smart applications on end devices. However, privacy-preserved computation is still expensive. Our investigation ha…
CHEETAH: An Ultra-Fast, Approximation-Free, and Privacy-Preserved Neural Network Framework based on Joint Obscure Linear and Nonlinear Computations
Qiao Zhang, Cong Wang, Chunsheng Xin +1
Machine Learning as a Service (MLaaS) is enabling a wide range of smart applications on end devices. However, such convenience comes with a cost of privacy because users have to up…