133 citations · 251 across the 26 of their papers we have counts for
28 papers
Guided Diffusion for Trustworthy Synthetic Text Generation
Qi Pang, Hanshen Xiao, Andre Manoel +4
The rapid evolution of Large Language Models is fueled by massive datasets, yet this reliance poses severe privacy risks, as models can inadvertently memorize and even directly out…
Self-Reflection Fine-Tuning: Enhancing Agent Security against Prompt Injection Attacks from Failure Experience
Zixuan Wang, Hao Li, Fengyu Gao +5
Large language model (LLM) agents are increasingly deployed in tool-augmented environments, but their reliance on external inputs makes them highly vulnerable to prompt injection a…
Trusted Hardware Acceleration for Function Secret Sharing
Pengzhi Huang, Kiwan Maeng, G. Edward Suh
Function secret sharing (FSS) is a core building block for privacy-preserving systems such as secure inference and private information retrieval (PIR), but incurs significant overh…
PIPES: Securing Agent Perception with Provenance and Priors
Sanjay Kariyappa, Severin Klingler, G. Edward Suh
Tool-using agents consume external data from sources with different levels of trust, yet tool responses rarely identify who produced each component or what it should convey. We sho…
Beyond Prediction: Tail-Aware Scheduling for LLM Inference
Yueying Li, Yuanfan Chen, Jiayang Chen +6
LLM serving exhibits extreme length variability, making size-based scheduling difficult in practice. Recent LLM schedulers approximate SJF/SRPT using predicted decode lengths or ra…
VIPIR: A Versatile GPU Framework for Integrating Private Information Retrieval Protocols
Jongmin Kim, Hyesung Ji, Jean-Luc Watson +3
While private information retrieval (PIR) enables private database services by fully concealing access patterns, it simultaneously requires high computational throughput, large mem…
Where Instruction Hierarchy Breaks: Diagnosing and Repairing Failures in Reasoning Language Models
Sanjay Kariyappa, G. Edward Suh
Reasoning language models deployed in agentic workflows must follow an instruction hierarchy: when instructions from different sources conflict, the model should obey the highest-p…
A Prior-Aware Metric for Efficiently Distinguishing Memorization from Generalization in Large Language Models
Trishita Tiwari, Ari Trachtenberg, G. Edward Suh
Training data leakage from Large Language Models (LLMs) raises serious concerns related to privacy, security, and copyright compliance. A central challenge in assessing this risk i…
Approximating ReLU on a Reduced Ring for Efficient MPC-based Private Inference
Kiwan Maeng, G. Edward Suh
Secure multi-party computation (MPC) allows users to offload machine learning inference on untrusted servers without having to share their privacy-sensitive data. Despite their str…
Towards Fast, Adaptive, and Hardware-Assisted User-Space Scheduling
Lisa, Li, Nikita Lazarev +7
Modern datacenter applications are prone to high tail latencies since their requests typically follow highly-dispersive distributions. Delivering fast interrupts is essential to re…
Information Flow Control in Machine Learning through Modular Model Architecture
Trishita Tiwari, Suchin Gururangan, Chuan Guo +7
In today's machine learning (ML) models, any part of the training data can affect the model output. This lack of control for information flow from training data to model output is…
Bounding the Invertibility of Privacy-preserving Instance Encoding using Fisher Information
Kiwan Maeng, Chuan Guo, Sanjay Kariyappa +1
Privacy-preserving instance encoding aims to encode raw data as feature vectors without revealing their privacy-sensitive information. When designed properly, these encodings can b…
Data Leakage via Access Patterns of Sparse Features in Deep Learning-based Recommendation Systems
Hanieh Hashemi, Wenjie Xiong, Liu Ke +4
Online personalized recommendation services are generally hosted in the cloud where users query the cloud-based model to receive recommended input such as merchandise of interest o…
DisaggRec: Architecting Disaggregated Systems for Large-Scale Personalized Recommendation
Liu Ke, Xuan Zhang, Benjamin Lee +2
Deep learning-based personalized recommendation systems are widely used for online user-facing services in production datacenters, where a large amount of hardware resources are pr…
Efficient Privacy-Preserving Machine Learning with Lightweight Trusted Hardware
Pengzhi Huang, Thang Hoang, Yueying Li +2
In this paper, we propose a new secure machine learning inference platform assisted by a small dedicated security processor, which will be easier to protect and deploy compared to…
Cocktail Party Attack: Breaking Aggregation-Based Privacy in Federated Learning using Independent Component Analysis
Sanjay Kariyappa, Chuan Guo, Kiwan Maeng +4
Federated learning (FL) aims to perform privacy-preserving machine learning on distributed data held by multiple data owners. To this end, FL requires the data owners to perform tr…
AutoCAT: Reinforcement Learning for Automated Exploration of Cache-Timing Attacks
Mulong Luo, Wenjie Xiong, Geunbae Lee +6
The aggressive performance optimizations in modern microprocessors can result in security vulnerabilities. For example, timing-based attacks in processor caches can steal secret ke…
Accelerating Path Planning for Autonomous Driving with Hardware-Assisted Memoization
Mulong Luo, G. Edward Suh
Path planning for autonomous driving with dynamic obstacles poses a challenge because it needs to perform a higher-dimensional search (with time-dimension) while still meeting real…
Verifiable Access Control for Augmented Reality Localization and Mapping
Shaowei Zhu, Hyo Jin Kim, Maurizio Monge +4
Localization and mapping is a key technology for bridging the virtual and physical worlds in augmented reality (AR). Localization and mapping works by creating and querying maps ma…
Structured Pruning is All You Need for Pruning CNNs at Initialization
Yaohui Cai, Weizhe Hua, Hongzheng Chen +3
Pruning is a popular technique for reducing the model size and computational cost of convolutional neural networks (CNNs). However, a slow retraining or fine-tuning procedure is of…
BulletTrain: Accelerating Robust Neural Network Training via Boundary Example Mining
Weizhe Hua, Yichi Zhang, Chuan Guo +2
Neural network robustness has become a central topic in machine learning in recent years. Most training algorithms that improve the model's robustness to adversarial and common cor…
Wireless Charging Power Side-Channel Attacks
Alexander S. La Cour, Khurram K. Afridi, G. Edward Suh
This paper shows that today's wireless charging interface is vulnerable to power side-channel attacks; a smartphone charging wirelessly leaks private information about its activity…
GuardNN: Secure Accelerator Architecture for Privacy-Preserving Deep Learning
Weizhe Hua, Muhammad Umar, Zhiru Zhang +1
This paper proposes GuardNN, a secure DNN accelerator that provides hardware-based protection for user data and model parameters even in an untrusted environment. GuardNN shows tha…
Strong Asymptotic Composition Theorems for Mutual Information Measures
Benjamin Wu, Aaron B. Wagner, Ibrahim Issa +1
We characterize the growth of the Sibson and Arimoto mutual informations and -maximal leakage, of any order that is at least unity, between a random variable and a growing set o…