Practical Implementation of Federated Learning for Detecting Backdoor Attacks in a Next-word Prediction Model
Sign Up to like & getrecommendations! Published in 2025 at "Scientific Reports"
DOI: 10.1038/s41598-024-82079-2
Abstract: This article details the development of a next-word prediction model utilizing federated learning and introduces a mechanism for detecting backdoor attacks. Federated learning enables multiple devices to collaboratively train a shared model while retaining data… read more here.
Keywords: backdoor attacks; word prediction; model; federated learning ... See more keywords
Improved Distributed Backdoor Attacks in Federated Learning by Density-Adaptive Data Poisoning and Projection-Based Gradient Updating
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Access"
DOI: 10.1109/access.2025.3586416
Abstract: While federated learning enables collaborative model training with preserved data locality, it remains vulnerable to evolving backdoor attacks that exploit its distributed architecture. Compared with centralized backdoor attacks, a distributed backdoor attack (DBA) poses a… read more here.
Keywords: backdoor attacks; attack; federated learning; distributed backdoor ... See more keywords
Collusive Backdoor Attacks in Federated Learning Frameworks for IoT Systems
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Internet of Things Journal"
DOI: 10.1109/jiot.2024.3368754
Abstract: Internet of Things (IoT) devices generate massive amounts of data from local devices, making federated learning (FL) a viable distributed machine learning paradigm to learn a global model while keeping private data locally in various… read more here.
Keywords: backdoor; backdoor attacks; iot systems; collusive backdoor ... See more keywords
Defense-Resistant Backdoor Attacks Against Deep Neural Networks in Outsourced Cloud Environment
Sign Up to like & getrecommendations! Published in 2021 at "IEEE Journal on Selected Areas in Communications"
DOI: 10.1109/jsac.2021.3087237
Abstract: The time and monetary costs of training sophisticated deep neural networks are exorbitant, which motivates resource-limited users to outsource the training process to the cloud. Concerning that an untrustworthy cloud service provider may inject backdoors… read more here.
Keywords: defense strategies; deep neural; neural networks; defense ... See more keywords
Coordinated Backdoor Attacks against Federated Learning with Model-Dependent Triggers
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Network"
DOI: 10.1109/mnet.011.2000783
Abstract: Federated learning enables distributed training of deep learning models among user equipment (UE) to obtain a high-quality global model. A centralized server aggregates the updates submitted by UEs without knowledge of the local training data… read more here.
Keywords: federated learning; model dependent; backdoor attacks; coordinated backdoor ... See more keywords
Interpretability-Guided Defense Against Backdoor Attacks to Deep Neural Networks
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"
DOI: 10.1109/tcad.2021.3111123
Abstract: As an emerging threat to deep neural networks (DNNs), backdoor attacks have received increasing attentions due to the challenges posed by the lack of transparency inherent in DNNs. In this article, we develop an efficient… read more here.
Keywords: deep neural; neural networks; backdoor attacks; interpretability guided ... See more keywords
Invisible Backdoor Attacks on Deep Neural Networks Via Steganography and Regularization
Sign Up to like & getrecommendations! Published in 2021 at "IEEE Transactions on Dependable and Secure Computing"
DOI: 10.1109/tdsc.2020.3021407
Abstract: Deep neural networks (DNNs) have been proven vulnerable to backdoor attacks, where hidden features (patterns) trained to a normal model, which is only activated by some specific input (called triggers), trick the model into producing… read more here.
Keywords: deep neural; neural networks; backdoor attacks; invisible backdoor ... See more keywords
Stealthy and Flexible Trojan in Deep Learning Framework
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Dependable and Secure Computing"
DOI: 10.1109/tdsc.2022.3164073
Abstract: Deep neural networks (DNNs) are increasingly used as the critical component of applications, bringing high computational costs. Many practitioners host their models on third-party platforms. This practice exposes DNNs to risks: A third party hosting… read more here.
Keywords: backdoor attacks; framework; deep learning; model ... See more keywords
Efficient and Secure Federated Learning Against Backdoor Attacks
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Dependable and Secure Computing"
DOI: 10.1109/tdsc.2024.3354736
Abstract: Due to the powerful representation ability and superior performance of Deep Neural Networks (DNN), Federated Learning (FL) based on DNN has attracted much attention from both academic and industrial fields. However, its transmitted plaintext data… read more here.
Keywords: backdoor; backdoor attacks; underline underline; secure ... See more keywords
Towards Practical Backdoor Attacks on Federated Learning Systems
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Dependable and Secure Computing"
DOI: 10.1109/tdsc.2024.3376790
Abstract: Federated Learning (FL) is nowadays one of the most promising paradigms for privacy-preserving distributed learning. Without revealing its local private data to outsiders, a client in FL systems collaborates to build a global Deep Neural… read more here.
Keywords: backdoor; backdoor attacks; attack; practical backdoor ... See more keywords
NTD: Non-Transferability Enabled Deep Learning Backdoor Detection
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Information Forensics and Security"
DOI: 10.1109/tifs.2023.3312973
Abstract: To mitigate recent insidious backdoor attacks on deep learning models, advances have been made by the research community. Nonetheless, state-of-the-art defenses are either limited to specific backdoor attacks (i.e., source-agnostic attacks) or non-user-friendly in that… read more here.
Keywords: detection; deep learning; input; backdoor attacks ... See more keywords