The paper proposes DP-LAC, a novel lightweight adaptive clipping technique for differentially private federated fine-tuning, which efficiently estimates and adapts the clipping threshold without consu…

The paper proposes Functional Subspace Watermarking (FSW), a robust method that embeds ownership signals into a stable, low-dimensional functional subspace of LLMs, significantly improving detection a…

This survey provides a comprehensive, structured taxonomy of split learning techniques for fine-tuning Large Language Models (LLMs), covering model optimization, system efficiency, and privacy preserv…

FedAttr introduces a novel client-level attribution protocol for Federated Learning (FL) that accurately identifies which clients trained on watermarked data while maintaining strong privacy guarantee…

This paper investigates the privacy risk of reconstructing Personally Identifiable Information (PII) from Large Language Models (LLMs) that have undergone Supervised Finetuning (SFT), proposing a nove…

SafeLM is a comprehensive framework that jointly addresses privacy, security, misinformation, and adversarial robustness in federated LLMs, achieving high safety performance while significantly reduci…

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 m…

The paper introduces ActInv and PAF to systematically analyze and quantify privacy leakage from intermediate activations during split inference of LLMs, proposing PriPert for enhanced defense.

The paper proposes an Augmented Model maniPulation (AugMP) strategy, utilizing graph representation learning, to effectively and stealthily manipulate federated fine-tuning of LLMs, significantly degr…

CachePrune introduces a privacy-aware, fine-grained KV cache sharing mechanism that allows LLM inference systems to safely reuse cache entries across users' requests, significantly improving efficienc…

The paper proposes FLRSP, a privacy-preserving federated learning method that enhances robustness by randomly selecting model parameters for global model updates, maintaining high accuracy against sta…

The paper introduces RLSpoofer, a lightweight, black-box reinforcement learning attack that demonstrates the fragile resilience of current LLM watermarking schemes by achieving a high spoofing success…

The paper proposes SSG, a novel logit-balanced vocabulary partitioning method, to enhance the watermark strength and detectability of LLM-generated content, especially in low-entropy domains like code…

The paper proposes FedPower, a novel differentially private cross-silo Federated Learning framework that uses PowerDP to reconstruct and project client updates into a secure low-rank space, effectivel…

The paper introduces Privacy-Preserving Fine-Tuning (PPFT), a novel two-stage pipeline that allows LLMs to process sensitive data via pooled embeddings rather than raw text, achieving a strong balance…

The paper introduces a Verifiable Gradient Inversion Attack (VGIA) that provides an explicit, certifiable method for reconstructing individual training records from shared gradients, particularly effe…

This paper conducts a structured ablation study using a unified threat model to evaluate how various system factors (like model architecture and retrieval configuration) influence different types of p…

This paper presents a novel data-free Membership Inference Attack (MIA) that uses gradient inversion on Standard Cell Library Layouts (SCLLs) to reconstruct sensitive hardware images from intercepted…

DP-FLogTinyLLM proposes a privacy-preserving federated framework for log anomaly detection that uses efficient Tiny LLMs, achieving high performance comparable to centralized methods while maintaining…

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