6 papers
MemLineage: Lineage-Guided Enforcement for LLM Agent Memory
Ciyan Ouyang, Rui Hou
We introduce MemLineage, a defense for LLM agent memory that attaches both cryptographic provenance and LLM-mediated derivation lineage to every entry. Recent and concurrent work s…
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…
virtCCA: Virtualized Arm Confidential Compute Architecture with TrustZone
Xiangyi Xu, Wenhao Wang, Yongzheng Wu +7
Arm introduced the Confidential Compute Architecture (CCA) in the upcoming Armv9-A architecture, enabling the support of confidential virtual machines (CVMs) in a separate world ca…
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…
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…
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…