8 papers · 1 filter
LoMime: Query-Efficient Membership Inference using Model Extraction in Label-Only Settings
Abdullah Caglar Oksuz, Anisa Halimi, Erman Ayday
Membership inference attacks (MIAs) threaten the privacy of machine learning models by revealing whether a specific data point was used during training. Existing MIAs often rely on…
Privacy Policy Enforcement Guardrails for Data-Sensitive Retrieval-Augmented Generation
Osama Zafar, Alexander Nemecek, Yiqian Zhang +5
Standard PII filters often miss contextual data leakage in RAG systems, such as non-regulated attribute clusters that collectively identify individuals. We introduce a Privacy Poli…
CausalGuard: Conformal Inference under Graph Uncertainty
Vikash Singh, Weicong Chen, Debargha Ganguly +12
Estimating treatment effects from observational data requires choosing an adjustment set, but valid adjustment depends on an unknown causal graph. Graph misspecification can cause…
Quantifying Memorization and Privacy Risks in Genomic Language Models
Alexander Nemecek, Wenbiao Li, Xiaoqian Jiang +2
Genomic language models (GLMs) have emerged as powerful tools for learning representations of DNA sequences, enabling advances in variant prediction, regulatory element identificat…
Comparing Reconstruction Attacks on Pretrained Versus Full Fine-tuned Large Language Model Embeddings on Homo Sapiens Splice Sites Genomic Data
Reem Al-Saidi, Erman Ayday, Ziad Kobti
This study investigates embedding reconstruction attacks in large language models (LLMs) applied to genomic sequences, with a specific focus on how fine-tuning affects vulnerabilit…
PQFed: A Privacy-Preserving Quality-Controlled Federated Learning Framework
Weiqi Yue, Wenbiao Li, Yuzhou Jiang +3
Federated learning enables collaborative model training without sharing raw data, but data heterogeneity consistently challenges the performance of the global model. Traditional op…