activity
20242026
collaborators

8 papers

cs.AI2026

Agentic evolution of physically constrained foundation models

Jiangwei Zhang, Wen Sun, Chong Wang +7

Artificial intelligence increasingly drives automated scientific discovery, yet contemporary generalist agents lack physical grounding, frequently hallucinating hardware-incompatib…

cs.CR2026

Janus: Compiler-Based Defense Against Transient Execution Attacks Using ARM Hardware Primitives

Ciyan Ouyang, Peinan Li, Yubiao Huang +2

We present Janus, a compiler-based security framework that mitigates transient execution attacks like Spectre and control-flow hijacking on ARM64 platforms. Janus integrates specul…

cs.CR2025

CryptPEFT: Efficient and Private Neural Network Inference via Parameter-Efficient Fine-Tuning

Saisai Xia, Wenhao Wang, Zihao Wang +4

Publicly available large pretrained models (i.e., backbones) and lightweight adapters for parameter-efficient fine-tuning (PEFT) have become standard components in modern machine l…

cs.CR2025

The Early Bird Catches the Leak: Unveiling Timing Side Channels in LLM Serving Systems

Linke Song, Zixuan Pang, Wenhao Wang +7

The wide deployment of Large Language Models (LLMs) has given rise to strong demands for optimizing their inference performance. Today's techniques serving this purpose primarily f…

cs.CR2025

Comet: Accelerating Private Inference for Large Language Model by Predicting Activation Sparsity

Guang Yan, Yuhui Zhang, Zimu Guo +6

With the growing use of large language models (LLMs) hosted on cloud platforms to offer inference services, privacy concerns about the potential leakage of sensitive information ar…

cs.CR2024

The Road to Trust: Building Enclaves within Confidential VMs

Wenhao Wang, Linke Song, Benshan Mei +6

Integrity is critical for maintaining system security, as it ensures that only genuine software is loaded onto a machine. Although confidential virtual machines (CVMs) function wit…