Jianrong Lu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jianrong Lu has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Hai Jin
Huazhong University of Science and Technology
2 shared publications - Leo Yu Zhang
School of Information and Communication Technology, Griffith University, Southport, Queensland, Australia
2 shared publications - Minghui Li
Huazhong University of Science and Technology
2 shared publications - Shengshan Hu
School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China
2 shared publications - Wei Wan
Faculty of Data Science, City University of Macau, Macau, China
2 shared publications Haohan Wang
1 shared publication
Latest Publications
- 31 October 2025
- Published by Springer Nature
- p. 153-164
TrustZone-Based WebAssembly Smart Contract Execution for Privacy-Preserving Blockchain
- 31 October 2025
- Published by Springer Nature
- p. 153-164
TrustZone-Based WebAssembly Smart Contract Execution for Privacy-Preserving Blockchain
- Open Access
- 31 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 19 (15566013) , 5405-5418
Depriving the Survival Space of Adversaries Against Poisoned Gradients in Federated Learning
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 corrupt the global model. Despite various defensive mechanisms having been developed to combat poisoning attacks, they all fall short of securing practical FL scenarios with heterogeneous and unbalanced data distribution. Moreover, the cutting-edge defenses currently at our disposal demand access to a proprietary dataset that closely mirrors the distribution of clients’ data, which runs counter to the fundamental principle of privacy protection in FL. It is still challenging to devise an effective defense approach that applies to practical FL. In this work, we strive to narrow the divide between FL defense and its practical use. We first present a general framework to comprehend the effect of poisoning attacks in FL when the training data is not independent and identically distributed (non-IID). We then HeteroFL, a novel FL scheme that incorporates four complementary defensive strategies. These tactics are implemented in succession to refine the aggregated model toward approaching the global optimum. Ultimately, we devise an adaptive attack specifically for HeteroFL, aimed at offering a more thorough evaluation of its robustness. Our extensive experiments over heterogeneous datasets and models show that HeteroFL surpasses all state-of-the-art defenses in thwarting various poisoning attacks, i.e., HeteroFL achieves global model accuracies comparable to the baseline, whereas other defenses suffer a significant accuracy reduction ranging from 34% to 79%.
- 31 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 19 (15566013) , 5405-5418
Open AccessDepriving the Survival Space of Adversaries Against Poisoned Gradients in Federated Learning
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 corrupt the global model. Despite various defensive mechanisms having been developed to combat poisoning attacks, they all fall short of securing practical FL scenarios with heterogeneous and unbalanced data distribution. Moreover, the cutting-edge defenses currently at our disposal demand access to a proprietary dataset that closely mirrors the distribution of clients’ data, which runs counter to the fundamental principle of privacy protection in FL. It is still challenging to devise an effective defense approach that applies to practical FL. In this work, we strive to narrow the divide between FL defense and its practical use. We first present a general framework to comprehend the effect of poisoning attacks in FL when the training data is not independent and identically distributed (non-IID). We then HeteroFL, a novel FL scheme that incorporates four complementary defensive strategies. These tactics are implemented in succession to refine the aggregated model toward approaching the global optimum. Ultimately, we devise an adaptive attack specifically for HeteroFL, aimed at offering a more thorough evaluation of its robustness. Our extensive experiments over heterogeneous datasets and models show that HeteroFL surpasses all state-of-the-art defenses in thwarting various poisoning attacks, i.e., HeteroFL achieves global model accuracies comparable to the baseline, whereas other defenses suffer a significant accuracy reduction ranging from 34% to 79%.
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 7394-7402
A Four-Pronged Defense Against Byzantine Attacks in Federated Learning
Federated learning (FL) is a nascent distributed learning paradigm to train a shared global model without violating users' privacy. FL has been shown to be vulnerable to various Byzantine attacks, where malicious participants could independently or collusively upload well-crafted updates to deteriorate the performance of the global model. However, existing defenses could only mitigate part of Byzantine attacks, without providing an all-sided shield for FL. It is difficult to simply combine them as they rely on totally contradictory assumptions. In this paper, we propose FPD, a four-pronged defense against both non-colluding and colluding Byzantine attacks. Our main idea is to utilize absolute similarity to filter updates rather than relative similarity used in existingI works. To this end, we first propose a reliable client selection strategy to prevent the majority of threats in the bud. Then we design a simple but effective score-based detection method to mitigate colluding attacks. Third, we construct an enhanced spectral-based outlier detector to accurately discard abnormal updates when the training data is not independent and identically distributed (non-IID). Finally, we design update denoising to rectify the direction of the slightly noisy but harmful updates. The four sequentially combined modules can effectively reconcile the contradiction in addressing non-colluding and colluding Byzantine attacks. Extensive experiments over three benchmark image classification datasets against four state-of-the-art Byzantine attacks demonstrate that FPD drastically outperforms existing defenses in IID and non-IID scenarios (with 30% improvement on model accuracy).
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 7394-7402
Open AccessA Four-Pronged Defense Against Byzantine Attacks in Federated Learning
Federated learning (FL) is a nascent distributed learning paradigm to train a shared global model without violating users' privacy. FL has been shown to be vulnerable to various Byzantine attacks, where malicious participants could independently or collusively upload well-crafted updates to deteriorate the performance of the global model. However, existing defenses could only mitigate part of Byzantine attacks, without providing an all-sided shield for FL. It is difficult to simply combine them as they rely on totally contradictory assumptions. In this paper, we propose FPD, a four-pronged defense against both non-colluding and colluding Byzantine attacks. Our main idea is to utilize absolute similarity to filter updates rather than relative similarity used in existingI works. To this end, we first propose a reliable client selection strategy to prevent the majority of threats in the bud. Then we design a simple but effective score-based detection method to mitigate colluding attacks. Third, we construct an enhanced spectral-based outlier detector to accurately discard abnormal updates when the training data is not independent and identically distributed (non-IID). Finally, we design update denoising to rectify the direction of the slightly noisy but harmful updates. The four sequentially combined modules can effectively reconcile the contradiction in addressing non-colluding and colluding Byzantine attacks. Extensive experiments over three benchmark image classification datasets against four state-of-the-art Byzantine attacks demonstrate that FPD drastically outperforms existing defenses in IID and non-IID scenarios (with 30% improvement on model accuracy).