The paper proposes RPSG, a method that uses private seeds and differential privacy to generate highly realistic and strongly privacy-preserving synthetic data replicas of private text for LLMs.

This paper empirically evaluates the effectiveness of Differential Privacy (DP) against Membership Inference Attacks (MIAs) in Federated Learning, demonstrating that a stacking attack strategy can det…

This paper evaluates multiple LLMs (DeepSeek-R1, OpenBioLLM-Llama3, Qwen 3.5) for generating privacy-safe, high-quality synthetic mental health reports, demonstrating their effectiveness in expanding…

The paper proposes using Differentially Private (DP) synthetic data, specifically through tabular synthesis and DP-Seeded Agent-Based Modeling (ABM), to resolve the conflict between data utility and p…

DPDSyn improves differentially private dataset synthesis by training a differentially private AI model on the original private data, which is then used to generate synthetic datasets that maintain hig…

The paper introduces a DNA-based cryptographic primitive that uses shared, sequenced DNA molecules to generate a common binary mask for One-Time Pad (OTP) encryption, achieving unconditional security…

The paper proposes a novel data transformation framework that creates semantically rich, privacy-preserving numeric views of EHR data, enabling large-scale research while provably breaking patient lin…

The paper proposes a hashing-based framework using Differential Privacy to generate and release private datastores for retrieval-augmented AI systems, achieving strong privacy with minimal accuracy lo…

The paper introduces SeedHijack, a backdoor attack that manipulates the pseudorandom number generation process in LLMs to force specific token selections, and proposes a hardware quantum random number…

The paper proposes an optimized, end-to-end privacy-preserving framework for vertical federated learning by distributing aggregation roles across multiple servers using secure multiparty computation a…

FedFG introduces a robust federated learning framework using flow-matching generation to simultaneously enhance client privacy and defend against sophisticated poisoning attacks.

PRAG is an end-to-end privacy-preserving Retrieval-Augmented Generation (RAG) system that maintains high retrieval accuracy and scalability in cloud environments by encrypting both documents and queri…

MetaMoE introduces a privacy-preserving framework that unifies independently trained, domain-specialized experts into a single Mixture-of-Experts (MoE) model using diversity-aware proxy data.

This paper proposes two post-processing techniques, random selection and linear combination, to construct a model that satisfies any desired differential privacy level without retraining, given a set…

This paper develops optimized algorithms and a pipeline architecture for high-throughput, memory-efficient batch processing of encrypted neural network inference, significantly improving performance o…

This paper proposes a comprehensive federated learning workflow that enhances privacy and robustness by integrating personalized differential privacy budgets and client drift detection, achieving bett…

The paper introduces extsc{Spore}, a novel, training-free, and highly efficient privacy extraction attack that targets sensitive information stored in the memory of LLM agents during inference, outpe…

The paper introduces HERALD, a token-level cryptographic redaction framework that encrypts only sensitive tokens in clinical text, enabling privacy-preserving LLM deployment without significant loss o…

The paper introduces ContinuousBench, a dynamic benchmark designed to rigorously test if differentially private (DP) synthetic text can genuinely transfer new knowledge and capabilities from sensitive…

The paper introduces ContinuousBench, a novel benchmark designed to rigorously test if differentially private (DP) synthetic text can genuinely transfer new knowledge, finding that state-of-the-art DP…