Viet Vo
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces ARES, a novel and practical gradient inversion attack that reconstructs sensitive training samples from large batch updates in Federated Learning without requiring architectural modifications.
The paper introduces MEntA, a highly query-efficient and surrogate-free membership inference attack that uses natural-language entailment to detect if a specific document was used by a RAG system, achieving high accuracy with only five queries.
Papers
Five Queries Are Enough: Query-Efficient and Surrogate-Free Membership Inference Attacks on RAG via Entailment
Nguyen Linh Bao Nguyen, Wanlun Ma, Viet Vo, Alsharif Abuadbba +3 more
The paper introduces MEntA, a highly query-efficient and surrogate-free membership inference attack that uses natural-language entailment to detect if a specific document was used by a RAG system, ach…