Copertina

Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstruction

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Shi, Shanghao, Wang, Ning, Xiao, Yang, Zhang, Chaoyu, Shi, Yi, Hou, Y. Thomas, Lou, Wenjing
Natura:	Preprint
Pubblicazione:	2023
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Enabling Trustworthy Federated Learning via Remote Attestation for Mitigating Byzantine Threats
di: Zhang, Chaoyu, et al.
Pubblicazione: (2025)

ProFLingo: A Fingerprinting-based Intellectual Property Protection Scheme for Large Language Models
di: Jin, Heng, et al.
Pubblicazione: (2024)

StarCast: A Secure and Spectrum-Efficient Group Communication Scheme for LEO Satellite Networks
di: Zhang, Chaoyu, et al.
Pubblicazione: (2025)

MedLeak: Multimodal Medical Data Leakage in Secure Federated Learning with Crafted Models
di: Shi, Shanghao, et al.
Pubblicazione: (2024)

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI
di: Jin, Heng, et al.
Pubblicazione: (2026)

BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learning
di: Jiang, Zhengyuan, et al.
Pubblicazione: (2024)

IU-GUARD: Privacy-Preserving Spectrum Coordination for Incumbent Users under Dynamic Spectrum Sharing
di: Li, Shaoyu, et al.
Pubblicazione: (2026)

Temporal Misalignment Attacks against Multimodal Perception in Autonomous Driving
di: Shahriar, Md Hasan, et al.
Pubblicazione: (2025)

ClawCoin: An Agentic AI-Native Cryptocurrency for Decentralized Agent Economies
di: Li, Shaoyu, et al.
Pubblicazione: (2026)

ARMOR 2025: A Military-Aligned Benchmark for Evaluating Large Language Model Safety Beyond Civilian Contexts
di: Johns, Sydney, et al.
Pubblicazione: (2026)

DarkMind: Latent Chain-of-Thought Backdoor in Customized LLMs
di: Guo, Zhen, et al.
Pubblicazione: (2025)

Two Heads Are Better than One: Model-Weight and Latent-Space Analysis for Federated Learning on Non-iid Data against Poisoning Attacks
di: Lyu, Xingyu, et al.
Pubblicazione: (2025)

AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments?
di: Li, Hao, et al.
Pubblicazione: (2026)

Per-element Secure Aggregation against Data Reconstruction Attacks in Federated Learning
di: Suimon, Takumi, et al.
Pubblicazione: (2025)

Let the Noise Speak: Harnessing Noise for a Unified Defense Against Adversarial and Backdoor Attacks
di: Shahriar, Md Hasan, et al.
Pubblicazione: (2024)

Enhancing Privacy of Spatiotemporal Federated Learning against Gradient Inversion Attacks
di: Zheng, Lele, et al.
Pubblicazione: (2024)

Model Inversion Attack against Federated Unlearning
di: Zhou, Lei, et al.
Pubblicazione: (2025)

Federated Domain Generalization with Latent Space Inversion
di: Palakkadavath, Ragja, et al.
Pubblicazione: (2025)

TraceGuard: Process-Guided Firewall against Reasoning Backdoors in Large Language Models
di: Guo, Zhen, et al.
Pubblicazione: (2026)

DDP-SA: Scalable Privacy-Preserving Federated Learning via Distributed Differential Privacy and Secure Aggregation
di: Wei, Wenjing, et al.
Pubblicazione: (2026)

GI-SMN: Gradient Inversion Attack against Federated Learning without Prior Knowledge
di: Qian, Jin, et al.
Pubblicazione: (2024)

ARES: Scalable and Practical Gradient Inversion Attack in Federated Learning through Activation Recovery
di: Gong, Zirui, et al.
Pubblicazione: (2026)

FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learning
di: Zhu, Gongxi, et al.
Pubblicazione: (2024)

Buffer is All You Need: Defending Federated Learning against Backdoor Attacks under Non-iids via Buffering
di: Lyu, Xingyu, et al.
Pubblicazione: (2025)

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models
di: Nguyen, Khanh, et al.
Pubblicazione: (2025)

Res-MIA: A Training-Free Resolution-Based Membership Inference Attack on Federated Learning Models
di: Zare, Mohammad, et al.
Pubblicazione: (2026)

SVDefense: Effective Defense against Gradient Inversion Attacks via Singular Value Decomposition
di: Luo, Chenxiang, et al.
Pubblicazione: (2025)

E-MIA: Exam-Style Black-Box Membership Inference Attacks against RAG Systems
di: Guan, Zelin, et al.
Pubblicazione: (2026)

Dealing Doubt: Unveiling Threat Models in Gradient Inversion Attacks under Federated Learning, A Survey and Taxonomy
di: Shi, Yichuan, et al.
Pubblicazione: (2024)

FAROS: Robust Federated Learning with Adaptive Scaling against Backdoor Attacks
di: Hu, Chenyu, et al.
Pubblicazione: (2026)

Scalable and Optimal Security Allocation in Networks against Stealthy Injection Attacks
di: Nguyen, Anh Tung, et al.
Pubblicazione: (2024)

Securing Federated Sensitive Topic Classification against Poisoning Attacks
di: Chu, Tianyue, et al.
Pubblicazione: (2022)

Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring
di: Hua, Peichun, et al.
Pubblicazione: (2025)

Low Rank Adaptation for Adversarial Perturbation
di: Liu, Han, et al.
Pubblicazione: (2026)

URVFL: Undetectable Data Reconstruction Attack on Vertical Federated Learning
di: Yao, Duanyi, et al.
Pubblicazione: (2024)

ReMIA: a Powerful and Efficient Alternative to Membership Inference Attacks against Synthetic Data Generators
di: Scassola, Davide, et al.
Pubblicazione: (2026)

Practical Feasibility of Gradient Inversion Attacks in Federated Learning
di: Valadi, Viktor, et al.
Pubblicazione: (2025)

Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization
di: Fang, Hao, et al.
Pubblicazione: (2026)

SeqMIA: Sequential-Metric Based Membership Inference Attack
di: Li, Hao, et al.
Pubblicazione: (2024)

On the Inference (In-)Security of Vertical Federated Learning: Efficient Auditing against Inference Tampering Attack
di: Huang, Chung-ju, et al.
Pubblicazione: (2025)