Analyzing the vulnerabilities in Split Federated Learning: assessing the robustness against data poisoning attacks
Sign Up to like & getrecommendations! Published in 2025 at "Scientific Reports"
DOI: 10.1038/s41598-025-15993-8
Abstract: Distributed Collaborative Machine Learning (DCML) offers a promising alternative to address privacy concerns in centralized machine learning. Split learning (SL) and Federated Learning (FL) are two effective learning approaches within DCML. Recently, there has been… read more here.
Keywords: data poisoning; split federated; attack; federated learning ... See more keywords
Log Poisoning Attacks in IoT: Methodologies, Evasion, Detection, Mitigation, and Criticality Analysis
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Access"
DOI: 10.1109/access.2024.3438383
Abstract: Log poisoning is a cyber-attack where adversaries manipulate systems’ log files to conceal their activities or execute malicious codes. This paper thoroughly examines log poisoning attacks, focusing on demonstrating methodologies applied to prevalent Internet of… read more here.
Keywords: poisoning attacks; log poisoning; criticality analysis; log ... See more keywords
A Robust and Efficient Federated Learning Algorithm Against Adaptive Model Poisoning Attacks
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Internet of Things Journal"
DOI: 10.1109/jiot.2024.3351371
Abstract: With the undetectable characteristic, adaptive model poisoning attacks can combine with any other attacks, bypassing the detection and violating the availability of federated learning (FL) systems. Existing defences are vulnerable to adaptive model poisoning attacks,… read more here.
Keywords: adaptive attacks; adaptive model; model poisoning; model ... See more keywords
Auditable Federated Learning With Byzantine Robustness
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Computational Social Systems"
DOI: 10.1109/tcss.2023.3266019
Abstract: Machine learning (ML) has led to disruptive innovations in many fields, such as medical diagnoses. A key enabler for ML is large training data, but existing data, such as medical data, are not fully exploited… read more here.
Keywords: byzantine robustness; privacy; client; federated learning ... See more keywords
Shielding Collaborative Learning: Mitigating Poisoning Attacks Through Client-Side Detection
Sign Up to like & getrecommendations! Published in 2021 at "IEEE Transactions on Dependable and Secure Computing"
DOI: 10.1109/tdsc.2020.2986205
Abstract: Collaborative learning allows multiple clients to train a joint model without sharing their data with each other. Each client performs training locally and then submits the model updates to a central server for aggregation. Since… read more here.
Keywords: detection; client side; poisoning attacks; collaborative learning ... See more keywords
Sine: Similarity is Not Enough for Mitigating Local Model Poisoning Attacks in Federated Learning
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Dependable and Secure Computing"
DOI: 10.1109/tdsc.2024.3353317
Abstract: Federated learning is a collaborative machine learning paradigm that brings the model to the edge for training over the participants’ local data under the orchestration of a trusted server. Though this paradigm protects data privacy,… read more here.
Keywords: model poisoning; similarity enough; model; sine similarity ... See more keywords
SHIELD - Secure Aggregation Against Poisoning in Hierarchical Federated Learning
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Transactions on Dependable and Secure Computing"
DOI: 10.1109/tdsc.2024.3472869
Abstract: Federated Learning (FL) is a privacy-preserving distributed Machine Learning (ML) technique. Hierarchical FL is a novel variant of FL applicable to networks with multiple layers. Instead of transmitting client models to the server, hierarchical FL… read more here.
Keywords: shield secure; hierarchical systems; federated learning; aggregation ... See more keywords
Poisoning Attacks and Defenses to Learned Bloom Filters for Malicious URL Detection
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Transactions on Dependable and Secure Computing"
DOI: 10.1109/tdsc.2025.3528993
Abstract: Approximate membership query (AMQ) structures represented by the Bloom Filter and its variants have been popularly researched in recent years. Researchers have recently combined machine learning with this type of structure to reduce space consumption… read more here.
Keywords: attacks defenses; bloom; learned bloom; bloom filters ... See more keywords
LGP: Layerwise Gradient Purify for Robust Federated Learning against Poisoning Attacks
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Transactions on Dependable and Secure Computing"
DOI: 10.1109/tdsc.2025.3604778
Abstract: Federated learning (FL) has become a promising framework for collaborative model training on devices while preserving privacy. However, despite its significant potential, it faces notable cyber threats, such as poisoning attacks and codenamed Byzantine clients.… read more here.
Keywords: gradient purify; layerwise gradient; model; federated learning ... See more keywords
FLCert: Provably Secure Federated Learning Against Poisoning Attacks
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Information Forensics and Security"
DOI: 10.1109/tifs.2022.3212174
Abstract: Due to its distributed nature, federated learning is vulnerable to poisoning attacks, in which malicious clients poison the training process via manipulating their local training data and/or local model updates sent to the cloud server,… read more here.
Keywords: provably secure; flcert provably; federated learning; secure federated ... See more keywords
Depriving the Survival Space of Adversaries Against Poisoned Gradients in Federated Learning
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Information Forensics and Security"
DOI: 10.1109/tifs.2024.3360869
Abstract: Federated learning (FL) allows clients at the edge to learn a shared global model without disclosing their private data. However, FL is susceptible to poisoning attacks, wherein an adversary injects tainted local models that ultimately… read more here.
Keywords: survival space; depriving survival; federated learning; global model ... See more keywords