Copertina

Understanding Data Reconstruction Leakage in Federated Learning from a Theoretical Perspective

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Zifan, Zhang, Binghui, Pang, Meng, Hong, Yuan, Wang, Binghui
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Cryptography and Security Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

On Google's SynthID-Text LLM Watermarking System: Theoretical Analysis and Empirical Validation
di: Omidi, Romina, et al.
Pubblicazione: (2026)

Inf2Guard: An Information-Theoretic Framework for Learning Privacy-Preserving Representations against Inference Attacks
di: Noorbakhsh, Sayedeh Leila, et al.
Pubblicazione: (2024)

A Learning-Based Attack Framework to Break SOTA Poisoning Defenses in Federated Learning
di: Yang, Yuxin, et al.
Pubblicazione: (2024)

Watermarking Graph Neural Networks via Explanations for Ownership Protection
di: Downer, Jane, et al.
Pubblicazione: (2025)

FedGMark: Certifiably Robust Watermarking for Federated Graph Learning
di: Yang, Yuxin, et al.
Pubblicazione: (2024)

SilentDrift: Exploiting Action Chunking for Stealthy Backdoor Attacks on Vision-Language-Action Models
di: Xu, Bingxin, et al.
Pubblicazione: (2026)

Breaking Secure Aggregation: Label Leakage from Aggregated Gradients in Federated Learning
di: Wang, Zhibo, et al.
Pubblicazione: (2024)

Theoretical Analysis of Privacy Leakage in Trustworthy Federated Learning: A Perspective from Linear Algebra and Optimization Theory
di: Zhang, Xiaojin, et al.
Pubblicazione: (2024)

Learning Robust and Privacy-Preserving Representations via Information Theory
di: Zhang, Binghui, et al.
Pubblicazione: (2024)

SoK: On Gradient Leakage in Federated Learning
di: Du, Jiacheng, et al.
Pubblicazione: (2024)

Distributed Backdoor Attacks on Federated Graph Learning and Certified Defenses
di: Yang, Yuxin, et al.
Pubblicazione: (2024)

Practicable Black-box Evasion Attacks on Link Prediction in Dynamic Graphs -- A Graph Sequential Embedding Method
di: Li, Jiate, et al.
Pubblicazione: (2024)

Understanding Secret Leakage Risks in Code LLMs: A Tokenization Perspective
di: Chen, Meifang, et al.
Pubblicazione: (2026)

MoCo-EA: Exploiting Adversarial Mode Connectivity for Efficient Evolutionary Attacks
di: Kim, Hyo Seo, et al.
Pubblicazione: (2026)

AGNNCert: Defending Graph Neural Networks against Arbitrary Perturbations with Deterministic Certification
di: Li, Jiate, et al.
Pubblicazione: (2025)

Burn-After-Use for Preventing Data Leakage through a Secure Multi-Tenant Architecture in Enterprise LLM
di: Zhang, Qiang, et al.
Pubblicazione: (2026)

Deterministic Certification of Graph Neural Networks against Graph Poisoning Attacks with Arbitrary Perturbations
di: Li, Jiate, et al.
Pubblicazione: (2025)

SafeGPT: Preventing Data Leakage and Unethical Outputs in Enterprise LLM Use
di: Desai, Pratyush, et al.
Pubblicazione: (2026)

Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks
di: Li, Jiate, et al.
Pubblicazione: (2025)

Data Valuation and Detections in Federated Learning
di: Li, Wenqian, et al.
Pubblicazione: (2023)

Efficient Byzantine-Robust and Provably Privacy-Preserving Federated Learning
di: Nie, Chenfei, et al.
Pubblicazione: (2024)

VeriSplit: Secure and Practical Offloading of Machine Learning Inferences across IoT Devices
di: Zhang, Han, et al.
Pubblicazione: (2024)

Backdoor Attacks on Discrete Graph Diffusion Models
di: Wang, Jiawen, et al.
Pubblicazione: (2025)

Privacy-Preserving Federated Learning from Partial Decryption Verifiable Threshold Multi-Client Functional Encryption
di: Wang, Minjie, et al.
Pubblicazione: (2025)

Universally Harmonizing Differential Privacy Mechanisms for Federated Learning: Boosting Accuracy and Convergence
di: Feng, Shuya, et al.
Pubblicazione: (2024)

OASIS: Offsetting Active Reconstruction Attacks in Federated Learning
di: Jeter, Tre' R., et al.
Pubblicazione: (2023)

UIFV: Data Reconstruction Attack in Vertical Federated Learning
di: Yang, Jirui, et al.
Pubblicazione: (2024)

Graph Neural Network Explanations are Fragile
di: Li, Jiate, et al.
Pubblicazione: (2024)

Certifiable Black-Box Attacks with Randomized Adversarial Examples: Breaking Defenses with Provable Confidence
di: Hong, Hanbin, et al.
Pubblicazione: (2023)

Defending Against Sophisticated Poisoning Attacks with RL-based Aggregation in Federated Learning
di: Wang, Yujing, et al.
Pubblicazione: (2024)

Paladin: Defending LLM-enabled Phishing Emails with a New Trigger-Tag Paradigm
di: Pang, Yan, et al.
Pubblicazione: (2025)

Towards Efficient Privacy-Preserving Machine Learning: A Systematic Review from Protocol, Model, and System Perspectives
di: Zeng, Wenxuan, et al.
Pubblicazione: (2025)

Approximate and Weighted Data Reconstruction Attack in Federated Learning
di: Song, Yongcun, et al.
Pubblicazione: (2023)

Understanding Byzantine Robustness in Federated Learning with A Black-box Server
di: Zhao, Fangyuan, et al.
Pubblicazione: (2024)

CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakage
di: Li, Na, et al.
Pubblicazione: (2025)

Beyond TVLA: Anderson-Darling Leakage Assessment for Neural Network Side-Channel Leakage Detection
di: Mikulec, Ján, et al.
Pubblicazione: (2026)

Automating Prompt Leakage Attacks on Large Language Models Using Agentic Approach
di: Sternak, Tvrtko, et al.
Pubblicazione: (2025)

Argus: A Multi-Agent Sensitive Information Leakage Detection Framework Based on Hierarchical Reference Relationships
di: Wang, Bin, et al.
Pubblicazione: (2025)

OptiLeak: Efficient Prompt Reconstruction via Reinforcement Learning in Multi-tenant LLM Services
di: Wang, Longxiang, et al.
Pubblicazione: (2026)

Towards Strong Certified Defense with Universal Asymmetric Randomization
di: Hong, Hanbin, et al.
Pubblicazione: (2025)