9 papers
Spectrum-Aware Bounds on Invertibility for Privacy-Enhancing Instance Encoding
Seokjin Hwang, Yuting, Li +1
Instance encoding is a popular empirical technique for privacy enhancement when sharing data to an untrusted server. It transforms sensitive data through an encoding process before…
Composition for Pufferfish Privacy
Jiamu Bai, Guanlin He, Xin Gu +2
When creating public data products out of confidential datasets, inferential/posterior-based privacy definitions, such as Pufferfish, provide compelling privacy semantics for data…
Characterization of Multi-Model Agentic AI Systems on General Tasks via Trace-Driven Simulation
Donghwan Kim, Prakhar Singh, Younghoon Min +3
Agentic AI completes tasks through iterative planning, tool use, and reasoning based on observed outcomes. Despite its popularity, its system-level behavior remains poorly understo…
Beyond Latency: A System-Level Characterization of MPC and FHE for PPML
Pengzhi Huang, Kiwan Maeng, G. Edward Suh
Privacy protection has become an increasing concern in modern machine learning applications. Privacy-preserving machine learning (PPML) has attracted growing research attention, wi…
Correlating Cross-Iteration Noise for DP-SGD using Model Curvature
Xin Gu, Yingtai Xiao, Guanlin He +3
Differentially private stochastic gradient descent (DP-SGD) offers the promise of training deep learning models while mitigating many privacy risks. However, there is currently a l…
CrypTorch: PyTorch-based Auto-tuning Compiler for Machine Learning with Multi-party Computation
Jinyu Liu, Gang Tan, Kiwan Maeng
MPC-based ML uses multi-party computation (MPC) to run machine learning (ML) workloads across multiple parties without each having to share their private data or model parameters.…