Hong Zhu
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
Hong Zhu has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Kai Chen
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
4 shared publications - Shengzhi Zhang
Department of Computer Science, Metropolitan College, Boston University, Boston, MA, USA
2 shared publications - Congyi Li
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
1 shared publication Jinwen He
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
1 shared publication- Peizhuo Lv
Nanyang technological university, Singapore, Singapore
1 shared publication Shengzhi Zhang
Department of Computer Science, Metropolitan College, Boston University, Boston, MA, USA
1 shared publication
Latest Publications
- 27 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 4816-4830
HEFLGuard: Backdoor Detection in Homomorphic Encryption-Based Federated Learning
Homomorphic encryption-based federated learning (HEFL) strengthens privacy by aggregating encrypted model updates, but it also renders existing backdoor defenses that assume plaintext updates inapplicable. We present HEFLGuard, a single-server backdoor detection framework for HEFL in which the server constructs overlapping validation models from encrypted client groups and clients locally compare logits of the global and validation models on benign samples to expose backdoor behavior. HEFLGuard further combines consistency verification across non-IID validation groups with Byzantine fault-tolerant aggregation of client reports, ensuring robustness under heterogeneous data and Byzantine participants. We evaluate HEFLGuard on seven vision/text benchmarks under three backdoor types across IID and non-IID settings. HEFLGuard consistently reduces ASR from near 100% to nearly the nobackdoor level while keeping the drop in clean accuracy within 2.5%. Compared with prior work, HEFLGuard achieves higher robustness and deployability.
- 27 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 4816-4830
HEFLGuard: Backdoor Detection in Homomorphic Encryption-Based Federated Learning
Homomorphic encryption-based federated learning (HEFL) strengthens privacy by aggregating encrypted model updates, but it also renders existing backdoor defenses that assume plaintext updates inapplicable. We present HEFLGuard, a single-server backdoor detection framework for HEFL in which the server constructs overlapping validation models from encrypted client groups and clients locally compare logits of the global and validation models on benign samples to expose backdoor behavior. HEFLGuard further combines consistency verification across non-IID validation groups with Byzantine fault-tolerant aggregation of client reports, ensuring robustness under heterogeneous data and Byzantine participants. We evaluate HEFLGuard on seven vision/text benchmarks under three backdoor types across IID and non-IID settings. HEFLGuard consistently reduces ASR from near 100% to nearly the nobackdoor level while keeping the drop in clean accuracy within 2.5%. Compared with prior work, HEFLGuard achieves higher robustness and deployability.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21, 8553-8568
Unveiling the Backdoor’s Suppression Effect for Backdoor Defence
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21, 8553-8568
Unveiling the Backdoor’s Suppression Effect for Backdoor Defence
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (1) , 1244-1259
AI-Shielder: Exploiting Backdoors to Defend Against Adversarial Attacks
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (1) , 1244-1259
AI-Shielder: Exploiting Backdoors to Defend Against Adversarial Attacks
- 17 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 19 (15566013) , 4970-4985
NeuralSanitizer: Detecting Backdoors in Neural Networks
Deep neural networks (DNNs) have been pervasively used in many areas, e.g., computer vision, speech recognition, natural language processing, etc. However, recent works show that they are vulnerable to backdoor/Trojan attacks, severely restricting their usage in various scenarios. In this paper, we propose NeuralSanitizer, a novel approach to detect and remove backdoors in DNNs, capable of capturing various triggers with better accuracy and higher efficiency. In particular, we identify two fundamental properties of triggers, i.e., their effectiveness in the backdoored model and ineffectiveness in other clean models, and design a novel objective function to reconstruct triggers based on them. Then we present a new approach that leverages transferability to identify adversarial patches that could be generated during trigger reconstruction, thus detecting backdoors more accurately. We evaluate NeuralSanitizer on real-world backdoored DNNs and achieve 2.1% FNR and 0.9% FPR on average, significantly outperforming the state-of-the-art works by 1~14 times. In addition, NeuralSanitizer can reconstruct triggers up to 25% of the size of the original inputs on average, compared to only 6~10% by existing works. Finally, NeuralSanitizer is also 1~25 times faster than existing works.
- 17 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 19 (15566013) , 4970-4985
NeuralSanitizer: Detecting Backdoors in Neural Networks
Deep neural networks (DNNs) have been pervasively used in many areas, e.g., computer vision, speech recognition, natural language processing, etc. However, recent works show that they are vulnerable to backdoor/Trojan attacks, severely restricting their usage in various scenarios. In this paper, we propose NeuralSanitizer, a novel approach to detect and remove backdoors in DNNs, capable of capturing various triggers with better accuracy and higher efficiency. In particular, we identify two fundamental properties of triggers, i.e., their effectiveness in the backdoored model and ineffectiveness in other clean models, and design a novel objective function to reconstruct triggers based on them. Then we present a new approach that leverages transferability to identify adversarial patches that could be generated during trigger reconstruction, thus detecting backdoors more accurately. We evaluate NeuralSanitizer on real-world backdoored DNNs and achieve 2.1% FNR and 0.9% FPR on average, significantly outperforming the state-of-the-art works by 1~14 times. In addition, NeuralSanitizer can reconstruct triggers up to 25% of the size of the original inputs on average, compared to only 6~10% by existing works. Finally, NeuralSanitizer is also 1~25 times faster than existing works.