14 papers
COMPASS: Membership Inference Attack Against Vision Large Language Models via Adaptive Noise Calibration
Damien Lo, Hong Kyu Lee, Ruixuan Liu +1
Vision large language models (VLLMs) are deployed in privacy-sensitive domains, raising training-data exposure concerns. Existing gray-box membership inference attacks (MIAs) commo…
Auditing the Privacy of Synthetic Gene Expression Data: A Unified Weighted-Distance Framework for No-Box Membership Inference
Owen Tucker, Lily Wang, Harutoshi Okumura +2
Synthetic gene expression data is increasingly proposed as a privacy-preserving substitute for controlled-access genomic repositories, but its safety depends on empirical auditing.…
PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration
Yuyang Xia, Ruixuan Liu, Li Xiong
Graph inference over relational data can expose sensitive edge information, and this risk becomes more severe in dynamic graphs, where repeated model updates cause privacy loss to…
Beyond Indistinguishability: Measuring Extraction Risk in LLM APIs
Ruixuan Liu, David Evans, Li Xiong
Indistinguishability properties such as differential privacy bounds or low empirically measured membership inference are widely treated as proxies to show a model is sufficiently p…
LLM-Driven Online Aggregation for Unstructured Text Analytics
Chao Hui, Weizheng Lu, Yanjie Gao +3
Large Language Models (LLMs) exhibit strong capabilities in text processing, and recent research has augmented SQL and DataFrame with LLM-powered semantic operators for data analys…
FusionDP: Foundation Model-Assisted Differentially Private Learning for Partially Sensitive Features
Linghui Zeng, Ruixuan Liu, Atiquer Rahman Sarkar +3
Ensuring the privacy of sensitive training data is crucial in privacy-preserving machine learning. However, in practical scenarios, privacy protection may be required for only a su…
FedSGT: Exact Federated Unlearning via Sequential Group-based Training
Bokang Zhang, Hong Guan, Hong kyu Lee +3
Federated Learning (FL) enables collaborative, privacy-preserving model training, but supporting the "Right to be Forgotten" is especially challenging because data influences the m…
SnapAudit: Active Auditing of Differentially Private In-Context Learning via Snapshot-Based Simulation
Yuyang Xia, Ruixuan Liu, Li Xiong
In-context learning (ICL) allows LLMs to adapt to new tasks via a few demonstrations, but those demonstrations may contain sensitive data. Differentially private (DP) ICL mechanism…
Direct Token Optimization: A Self-contained Approach to Large Language Model Unlearning
Hong kyu Lee, Ruixuan Liu, Li Xiong
Machine unlearning is an emerging technique that removes the influence of a subset of training data (forget set) from a model without full retraining, with applications including p…
UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run
Ruixuan Liu, Li Xiong
Differentially private (DP) optimization has been widely adopted as a standard approach to provide rigorous privacy guarantees for training datasets. DP auditing verifies whether a…
Privacy and Accuracy-Aware AI/ML Model Deduplication
Hong Guan, Lei Yu, Lixi Zhou +5
With the growing adoption of privacy-preserving machine learning algorithms, such as Differentially Private Stochastic Gradient Descent (DP-SGD), training or fine-tuning models on…
Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Training
Toan Tran, Ruixuan Liu, Li Xiong
Large language models (LLMs) have become the backbone of modern natural language processing but pose privacy concerns about leaking sensitive training data. Membership inference at…
ExpShield: Safeguarding Web Text from Unauthorized Crawling and LLM Exploitation
Ruixuan Liu, Toan Tran, Tianhao Wang +3
As large language models increasingly memorize web-scraped training content, they risk exposing copyrighted or private information. Existing protections require compliance from cra…
Differentially Private Tabular Data Synthesis using Large Language Models
Toan V. Tran, Li Xiong
Synthetic tabular data generation with differential privacy is a crucial problem to enable data sharing with formal privacy. Despite a rich history of methodological research and d…