Privacy
Differential privacy, federated learning, and privacy-preserving ML
20 papers indexed
Digital Privacy in IoT: Exploring Challenges, Approaches and Open Issues
This paper analyzes digital privacy risks in IoT ecosystems, proposing a comprehensive framework (AURA-IoT) and taxonomy to mitigate threats using advanced privacy-enhancing technologies.
FedFG: Privacy-Preserving and Robust Federated Learning via Flow-Matching Generation
FedFG introduces a robust federated learning framework using flow-matching generation to simultaneously enhance client privacy and defend against sophisticated poisoning attacks.
DDP-SA: Scalable Privacy-Preserving Federated Learning via Distributed Differential Privacy and Secure Aggregation
DDP-SA is a novel federated learning framework that combines local differential privacy and secure aggregation to achieve robust, scalable, and highly private model training.
Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation
The paper proposes PINA, a two-stage differentially private clustered federated learning framework that improves convergence and robustness by using low-rank adaptation and a normality-driven aggregat…
Towards Privacy-Preserving Federated Learning using Hybrid Homomorphic Encryption
Ivan Costa, Pedro Correia, Ivone Amorim, Eva Maia +1 more
This paper enhances Federated Learning privacy by integrating two key protection mechanisms—masking and RSA encapsulation—into Hybrid Homomorphic Encryption (HHE) to secure against malicious clients.
Toward verifiably private learning from federated data
Katharine Daly, Yu Xiao, Zachary Garrett, Brett McLarnon +8 more
The paper presents a next-generation Federated Learning system that provides externally verifiable central Differential Privacy guarantees while improving device coverage and privacy-utility tradeoff.
Private Seeds, Public LLMs: Realistic and Privacy-Preserving Synthetic Data Generation
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.
FedAttr: Towards Privacy-preserving Client-Level Attribution in Federated LLM Fine-tuning
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…
Improving Parameter-Efficient Federated Learning with Differentially Private Refactorization
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…
Choose Wisely and Privately: Proactive Client Selection for Fair and Efficient Federated Learning
The paper proposes a proactive client selection framework that optimizes the selection of client subsets to ensure high data utility and fairness before federated learning begins, leading to faster an…
Towards Secure Retrieval-Augmented Generation: A Comprehensive Review of Threats, Defenses and Benchmarks
Yanming Mu, Hao Hu, Feiyang Li, Qiao Yuan +6 more
This paper provides the first comprehensive, end-to-end survey dedicated to the security of Retrieval-Augmented Generation (RAG) systems, systematically mapping threats, defenses, and benchmarks acros…
PAC-DP: Personalized Adaptive Clipping for Differentially Private Federated Learning
The paper proposes PAC-DP, a personalized adaptive clipping framework that dynamically adjusts gradient clipping thresholds based on the desired privacy budget, significantly improving the privacy-uti…
Multi-Objective Submodular Maximization with Differential Privacy
Ting Hou, Yanhao Wang, Yiping Wang, Cen Chen +2 more
This paper addresses the challenging problem of multi-objective submodular maximization under a cardinality constraint while ensuring differential privacy, proposing novel algorithms with approximatio…
PrivFedTalk: Privacy-Aware Federated Diffusion with Identity-Stable Adapters for Personalized Talking-Head Generation
PrivFedTalk introduces a privacy-aware federated framework for personalized talking-head generation by combining a shared diffusion backbone with local LoRA identity adapters and robust aggregation te…
DP-FlogTinyLLM: Differentially private federated log anomaly detection using Tiny LLMs
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…
Differentially Private Datastore Generation for Retrieval-Augmented Inference
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…
Your Privacy My Cloak: Backdoor Attacks on Differentially Private Federated Learning
This paper challenges the assumption that differential privacy enhances the robustness of federated learning against backdoor attacks and proposes a novel attack called RING.
SoK: Practical Aspects of Releasing Differentially Private Graphs
This paper provides a comprehensive, practitioner-oriented framework and survey to guide the selection and evaluation of differentially private methods for releasing sensitive graph data.
DP-SelFT: Differentially Private Selective Fine-Tuning for Large Language Models
Haichao Sha, Zihao Wang, Yuncheng Wu, Hong Chen +1 more
The paper proposes DP-SelFT, a novel framework for differentially private selective fine-tuning that significantly improves the privacy-utility trade-off for LLMs by intelligently selecting robust par…
Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions
The paper proposes Byz-Clip21-SGD2M, a novel algorithm that achieves high-probability convergence guarantees for Federated Learning by integrating robust aggregation, double momentum, and clipping, re…