4 papers
MIA-EPT: Membership Inference Attack via Error Prediction for Tabular Data
Eyal German, Daniel Samira, Yuval Elovici +1
Synthetic data generation plays an important role in enabling data sharing, particularly in sensitive domains like healthcare and finance. Recent advances in diffusion models have…
LexiMark: Robust Watermarking via Lexical Substitutions to Enhance Membership Verification of an LLM's Textual Training Data
Eyal German, Sagiv Antebi, Edan Habler +2
Large language models (LLMs) can be trained or fine-tuned on data obtained without the owner's consent. Verifying whether a specific LLM was trained on particular data instances or…
Tab-MIA: A Benchmark Dataset for Membership Inference Attacks on Tabular Data in LLMs
Eyal German, Sagiv Antebi, Daniel Samira +2
Large language models (LLMs) are increasingly trained on tabular data, which, unlike unstructured text, often contains personally identifiable information (PII) in a highly structu…
MoE-MLoRA for Multi-Domain CTR Prediction: Efficient Adaptation with Expert Specialization
Ken Yaggel, Eyal German, Aviel Ben Siman Tov
Personalized recommendation systems must adapt to user interactions across different domains. Traditional approaches like MLoRA apply a single adaptation per domain but lack flexib…