8 papers
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…
PrivFusion: A Privacy-preserving Multi-Agent Framework for Harmonizing Distributed Datasets
Anisa Halimi, Liubov Nedoshivina, Kieran Fraser +1
The growing availability of clinical data has increased the use of machine learning, yet centralized data aggregation is often infeasible for sensitive health information. Federate…
Persona-Conditioned Adversarial Prompting (PCAP): Multi-Identity Red-Teaming for Enhanced Adversarial Prompt Discovery
Cristian Morasso, Anisa Halimi, Muhammad Zaid Hameed +1
Existing automated red-teaming pipelines often miss attacks that depend on attacker identity, framing, or multi-turn tactics. This under-coverage underestimates real-world risk. We…
Persona-Conditioned Adversarial Prompting: Multi-Identity Red-Teaming for Adversarial Discovery and Mitigation
Cristian Morasso, Anisa Halimi, Muhammad Zaid Hameed +1
Automated red-teaming for LLMs often discovers narrow attack slices, missing diverse real-world threats, and yielding insufficient data for safety fine-tuning. We introduce Persona…
In-Context Bias Propagation in LLM-Based Tabular Data Generation
Pol G. Recasens, Alberto Gutierrez, Jordi Torres +4
Large Language Models (LLMs) are increasingly used for synthetic tabular data generation through in-context learning (ICL), offering a practical solution for data augmentation in d…
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…