219 citations · 332 across the 16 of their papers we have counts for
16 papers
PrivacyGuard: A Modular Framework for Privacy Auditing in Machine Learning
Luca Melis, Matthew Grange, Iden Kalemaj +4
The increasing deployment of Machine Learning (ML) models in sensitive domains motivates the need for robust, practical privacy assessment tools. PrivacyGuard is a comprehensive to…
Differentially Private Federated Clustering with Random Rebalancing
Xiyuan Yang, Shengyuan Hu, Soyeon Kim +1
Federated clustering aims to group similar clients into clusters and produce one model for each cluster. Such a personalization approach typically improves model performance compar…
Enhancing One-run Privacy Auditing with Quantile Regression-Based Membership Inference
Terrance Liu, Matteo Boglioni, Yiwei Fu +3
Differential privacy (DP) auditing aims to provide empirical lower bounds on the privacy guarantees of DP mechanisms like DP-SGD. While some existing techniques require many traini…
BLUR: A Benchmark for LLM Unlearning Robust to Forget-Retain Overlap
Shengyuan Hu, Neil Kale, Pratiksha Thaker +3
Machine unlearning has the potential to improve the safety of large language models (LLMs) by removing sensitive or harmful information post hoc. A key challenge in unlearning invo…
Position: LLM Unlearning Benchmarks are Weak Measures of Progress
Pratiksha Thaker, Shengyuan Hu, Neil Kale +3
Unlearning methods have the potential to improve the privacy and safety of large language models (LLMs) by removing sensitive or harmful information post hoc. The LLM unlearning re…
Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning
Shengyuan Hu, Yiwei Fu, Zhiwei Steven Wu +1
Machine unlearning is a promising approach to mitigate undesirable memorization of training data in ML models. However, in this work we show that existing approaches for unlearning…
Privacy Amplification for the Gaussian Mechanism via Bounded Support
Shengyuan Hu, Saeed Mahloujifar, Virginia Smith +2
Data-dependent privacy accounting frameworks such as per-instance differential privacy (pDP) and Fisher information loss (FIL) confer fine-grained privacy guarantees for individual…
Guardrail Baselines for Unlearning in LLMs
Pratiksha Thaker, Yash Maurya, Shengyuan Hu +2
Recent work has demonstrated that finetuning is a promising approach to 'unlearn' concepts from large language models. However, finetuning can be expensive, as it requires both gen…
No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices
Qi Pang, Shengyuan Hu, Wenting Zheng +1
Advances in generative models have made it possible for AI-generated text, code, and images to mirror human-generated content in many applications. Watermarking, a technique that a…
Federated Learning as a Network Effects Game
Shengyuan Hu, Dung Daniel Ngo, Shuran Zheng +2
Federated Learning (FL) aims to foster collaboration among a population of clients to improve the accuracy of machine learning without directly sharing local data. Although there h…
On Privacy and Personalization in Cross-Silo Federated Learning
Ziyu Liu, Shengyuan Hu, Zhiwei Steven Wu +1
While the application of differential privacy (DP) has been well-studied in cross-device federated learning (FL), there is a lack of work considering DP and its implications for cr…
FedSynth: Gradient Compression via Synthetic Data in Federated Learning
Shengyuan Hu, Jack Goetz, Kshitiz Malik +3
Model compression is important in federated learning (FL) with large models to reduce communication cost. Prior works have been focusing on sparsification based compression that co…
Fair Federated Learning via Bounded Group Loss
Shengyuan Hu, Zhiwei Steven Wu, Virginia Smith
Fair prediction across protected groups is an important constraint for many federated learning applications. However, prior work studying group fair federated learning lacks formal…
Private Multi-Task Learning: Formulation and Applications to Federated Learning
Shengyuan Hu, Zhiwei Steven Wu, Virginia Smith
Many problems in machine learning rely on multi-task learning (MTL), in which the goal is to solve multiple related machine learning tasks simultaneously. MTL is particularly relev…
Ditto: Fair and Robust Federated Learning Through Personalization
Tian Li, Shengyuan Hu, Ahmad Beirami +1
Fairness and robustness are two important concerns for federated learning systems. In this work, we identify that robustness to data and model poisoning attacks and fairness, measu…
A New Defense Against Adversarial Images: Turning a Weakness into a Strength
Tao Yu, Shengyuan Hu, Chuan Guo +2
Natural images are virtually surrounded by low-density misclassified regions that can be efficiently discovered by gradient-guided search --- enabling the generation of adversarial…