Buchumschlag

A Taxonomy of Attacks and Defenses in Split Learning

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Shabbir, Aqsa, Kanpak, Halil İbrahim, Küpçü, Alptekin, Sav, Sinem
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Cryptography and Security Machine Learning
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

CURE: Privacy-Preserving Split Learning Done Right
von: Kanpak, Halil Ibrahim, et al.
Veröffentlicht: (2024)

SplitOut: Out-of-the-Box Training-Hijacking Detection in Split Learning via Outlier Detection
von: Erdogan, Ege, et al.
Veröffentlicht: (2023)

Byzantines can also Learn from History: Fall of Centered Clipping in Federated Learning
von: Ozfatura, Kerem, et al.
Veröffentlicht: (2022)

Aggressive or Imperceptible, or Both: Network Pruning Assisted Hybrid Byzantines in Federated Learning
von: Ozfatura, Emre, et al.
Veröffentlicht: (2024)

Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Data
von: Akkus, Atilla, et al.
Veröffentlicht: (2024)

Bridging Local and Federated Data Normalization in Federated Learning: A Privacy-Preserving Approach
von: Coşğun, Melih, et al.
Veröffentlicht: (2025)

How to Privately Tune Hyperparameters in Federated Learning? Insights from a Benchmark Study
von: Mitic, Natalija, et al.
Veröffentlicht: (2024)

AggFT: Low-Cost Fault-Tolerant Smart Meter Aggregation with Proven Termination and Privacy
von: Eibl, Günther, et al.
Veröffentlicht: (2021)

Attack and Defense of Deep Learning Models in the Field of Web Attack Detection
von: Shi, Lijia, et al.
Veröffentlicht: (2024)

SecureLearn -- An Attack-agnostic Defense for Multiclass Machine Learning Against Data Poisoning Attacks
von: Paracha, Anum, et al.
Veröffentlicht: (2025)

Uncovering Attacks and Defenses in Secure Aggregation for Federated Deep Learning
von: Zhang, Yiwei, et al.
Veröffentlicht: (2024)

Passive Inference Attacks on Split Learning via Adversarial Regularization
von: Zhu, Xiaochen, et al.
Veröffentlicht: (2023)

Data Reconstruction Attacks and Defenses: A Systematic Evaluation
von: Liu, Sheng, et al.
Veröffentlicht: (2024)

A No-Defense Defense Against Gradient-Based Adversarial Attacks on ML-NIDS: Is Less More?
von: elShehaby, Mohamed, et al.
Veröffentlicht: (2026)

KDk: A Defense Mechanism Against Label Inference Attacks in Vertical Federated Learning
von: Arazzi, Marco, et al.
Veröffentlicht: (2024)

SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)
von: Rieger, Phillip, et al.
Veröffentlicht: (2025)

Synthetic Tabular Data: Methods, Attacks and Defenses
von: Cormode, Graham, et al.
Veröffentlicht: (2025)

Exploiting Defenses against GAN-Based Feature Inference Attacks in Federated Learning
von: Luo, Xinjian, et al.
Veröffentlicht: (2020)

PECAN: A Deterministic Certified Defense Against Backdoor Attacks
von: Zhang, Yuhao, et al.
Veröffentlicht: (2023)

A Data-Driven Defense against Edge-case Model Poisoning Attacks on Federated Learning
von: Purohit, Kiran, et al.
Veröffentlicht: (2023)

Dashed Line Defense: Plug-And-Play Defense Against Adaptive Score-Based Query Attacks
von: Fu, Yanzhang, et al.
Veröffentlicht: (2026)

Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents
von: Zhan, Qiusi, et al.
Veröffentlicht: (2025)

A Defensive Framework Against Adversarial Attacks on Machine Learning-Based Network Intrusion Detection Systems
von: Tafreshian, Benyamin, et al.
Veröffentlicht: (2025)

A Multi-Agent LLM Defense Pipeline Against Prompt Injection Attacks
von: Hossain, S M Asif, et al.
Veröffentlicht: (2025)

Open-Weight LLM Fine-Tuning Defenses are Susceptible to Simple Attacks
von: Kuo, Kevin, et al.
Veröffentlicht: (2026)

Thwarting Cybersecurity Attacks with Explainable Concept Drift
von: Shaer, Ibrahim, et al.
Veröffentlicht: (2024)

Adversarial Threats in Quantum Machine Learning: A Survey of Attacks and Defenses
von: Ghosh, Archisman, et al.
Veröffentlicht: (2025)

Inferring Sensitive Attributes from Knowledge Graph Embeddings: Attack and Defense Strategies
von: Hayder, Yasmine
Veröffentlicht: (2026)

AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
von: Debenedetti, Edoardo, et al.
Veröffentlicht: (2024)

A Zero Trust Framework for Realization and Defense Against Generative AI Attacks in Power Grid
von: Munir, Md. Shirajum, et al.
Veröffentlicht: (2024)

SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning
von: Zhang, Heyi, et al.
Veröffentlicht: (2025)

FedMID: A Data-Free Method for Using Intermediate Outputs as a Defense Mechanism Against Poisoning Attacks in Federated Learning
von: Han, Sungwon, et al.
Veröffentlicht: (2024)

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

Sponge Attacks on Sensing AI: Energy-Latency Vulnerabilities and Defense via Model Pruning
von: Hasan, Syed Mhamudul, et al.
Veröffentlicht: (2025)

Dummy-Aware Weighted Attack (DAWA): Breaking the Safe Sink in Dummy Class Defenses
von: Yu, Yunrui, et al.
Veröffentlicht: (2026)

Test-time Adversarial Defense with Opposite Adversarial Path and High Attack Time Cost
von: Yeh, Cheng-Han, et al.
Veröffentlicht: (2024)

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

AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
von: Zeng, Yifan, et al.
Veröffentlicht: (2024)

Attacks and Defenses Against LLM Fingerprinting
von: Kurian, Kevin, et al.
Veröffentlicht: (2025)

Temporal Context Awareness: A Defense Framework Against Multi-turn Manipulation Attacks on Large Language Models
von: Kulkarni, Prashant, et al.
Veröffentlicht: (2025)