Intelligent Systems Software Lab
Intelligent Systems Software Lab
News
People
Publications
Projects
Events
Awards
Join us
Contact
Paper-Conference
Sweet or Sour CHERI: Performance Characterization of the Arm Morello Platform
Abstract Capability Hardware Enhanced RISC Instructions (CHERI) offer a hardware-based approach to enhance memory safety by enforcing strong spatial and temporal memory protections. This paper presents the largest performance analysis of the CHERI architecture on the ARM Morello platform seen to date.
Dr. Xiaoyang Sun
,
Jeremy Singer
,
Zheng Wang
MetaGuardian: Enhancing Voice Assistant Security through Advanced Acoustic Metamaterial
Abstract We present MetaGuardian, the first system to leverage acoustic metamaterials to protect voice assistants (VAs) against all three major classes of attacks - inaudible, adversarial, and laser-based - within a single, portable design.
Zhiyuan Ning
,
Zheng Wang
,
Zhanyong Tang
Code
Dataset
SecureMind: A Framework for Benchmarking Large Language Models in Memory Bug Detection and Repair
Abstract Large language models (LLMs) hold great promise for automating software vulnerability detection and repair, but ensuring their correctness remains a challenge. While recent work has developed benchmarks for evaluating LLMs in bug detection and repair, existing studies rely on hand-crafted datasets that quickly become outdated.
Huanting Wang
,
Dejice Jacob
,
David Kelly
,
Yehia Elkhatib
,
Jeremy Singer
,
Zheng Wang
Code
Dataset
Dataflow-Guided Neuro-Symbolic Language Models for Type Inference
Abstract Language Models (LMs) are increasingly used for type inference, aiding in error detection and software development. Some real-life deployments of LMs require the model to run on local machines to safeguard software’s intellectual property.
Gen Li
,
Yao Wan
,
Hongyu Zhang
,
Zhou Zhao
,
Wenbin Jiang
,
Xuanhua Shi
,
Hai Jin
,
Zheng Wang
Code
Dataset
Optimizing Personalized Federated Learning through Adaptive Layer-Wise Learning
Abstract Real-life deployment of federated Learning (FL) often faces non-IID data, which leads to poor accuracy and slow convergence. Personalized FL (pFL) tackles these issues by tailoring local models to individual data sources and using weighted aggregation methods for client-specific learning.
Weihang Chen
,
Cheng Yang
,
Zhiqiang Li
,
Jie Ren
»
Cite
×