3 papers
cs.LG2026
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…
cs.CR2026
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.…
cs.CR2026
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…