SPA: A poisoning attack framework for graph neural networks through searching and pairing
Sign Up to like & getrecommendations! Published in 2025 at "Machine Learning"
DOI: 10.1007/s10994-024-06706-9
Abstract: Graph Neural Networks (GNN) have played an important role in many fields, while GNNs also suffer from adversarial attacks that aim to malfunction the GNN model by changing the adjacency matrix (i.e. generating adversarial edges)… read more here.
Keywords: attack; adversarial edges; graph neural; poisoning attack ... See more keywords
PoisonGAN: Generative Poisoning Attacks Against Federated Learning in Edge Computing Systems
Sign Up to like & getrecommendations! Published in 2021 at "IEEE Internet of Things Journal"
DOI: 10.1109/jiot.2020.3023126
Abstract: Edge computing is a key-enabling technology that meets continuously increasing requirements for the intelligent Internet-of-Things (IoT) applications. To cope with the increasing privacy leakages of machine learning while benefiting from unbalanced data distributions, federated learning… read more here.
Keywords: poisoning attack; federated learning; generative poisoning; attack ... See more keywords
Efficiently Achieving Privacy Preservation and Poisoning Attack Resistance in Federated Learning
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Information Forensics and Security"
DOI: 10.1109/tifs.2024.3378006
Abstract: Federated learning enables clients to train models locally and provide local updates to the server instead of raw dataset, thereby preserving data privacy to some extent. However, adversaries can still pry users’ privacy by inferring… read more here.
Keywords: privacy preservation; attack; poisoning attack; secure ... See more keywords
Enhanced Model Poisoning Attack and Multi-Strategy Defense in Federated Learning
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Transactions on Information Forensics and Security"
DOI: 10.1109/tifs.2025.3555193
Abstract: As a new paradigm of distributed learning, Federated Learning (FL) has been applied in industrial fields, such as intelligent retail, finance and autonomous driving. However, several schemes that aim to attack robust aggregation rules and… read more here.
Keywords: attack; enhanced model; poisoning attack; model poisoning ... See more keywords
DamPa: Dynamic Adaptive Model Poisoning Attack in Federated Learning
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Transactions on Information Forensics and Security"
DOI: 10.1109/tifs.2025.3631449
Abstract: Federated learning (FL) enables cross-device collaboration by sharing local model updates without exposing raw data. However, its distributed nature introduces complex, multi-layered security threats that threaten both data privacy and model robustness. One of the… read more here.
Keywords: poisoning attack; dynamic adaptive; model poisoning; model ... See more keywords
ADFL: A Poisoning Attack Defense Framework for Horizontal Federated Learning
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Industrial Informatics"
DOI: 10.1109/tii.2022.3156645
Abstract: Recently, federated learning has received widespread attention, which will promote the implementation of artificial intelligence technology in various fields. Privacy-preserving technologies are applied to users’ local models to protect users’ privacy. Such operations make the… read more here.
Keywords: horizontal federated; attack defense; federated learning; poisoning attack ... See more keywords
LOKI: A Practical Data Poisoning Attack Framework Against Next Item Recommendations
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Knowledge and Data Engineering"
DOI: 10.1109/tkde.2022.3181270
Abstract: Due to the openness of the online platform, recommendation systems are vulnerable to data poisoning attacks, where malicious samples are injected into the training set of the recommendation system to manipulate its recommendation results. Existing… read more here.
Keywords: system; recommendation; recommendation systems; poisoning attack ... See more keywords
GCPA: GAN-Based Collusive Poisoning Attack in Federated Recommender Systems
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Transactions on Knowledge and Data Engineering"
DOI: 10.1109/tkde.2025.3579807
Abstract: Federated Recommender Systems (FedRecs) have evolved as a privacy-preserving paradigm that facilitates distributed training of personalized recommenders without sharing user data. However, FedRecs are known to be susceptible to poisoning attacks by malicious users, who… read more here.
Keywords: federated recommender; attack; gan based; poisoning attack ... See more keywords