I am currently an associate professor at the School of Cyber Science and Engineering, Xi’an Jiaotong University. I received my Ph.D. degree from the University of Technology Sydney, Australia. My research focuses on AI Security and Privacy, specifically, trustworthy AI and data privacy, model robustness and system security. During my Ph.D, I mainly focused on machine unlearning.

1. Machine Unlearning:
   • New Algorithms for Machine Unlearning and Federated Unlearning
   • Prevent Privacy Leakage during Machine Unlearning
   • Auditing and Verification of Machine Unlearning

News

• [May 2026] One paper about approximate unlearning with manifold representation was accepted by KDD 2026: Approximate Machine Unlearning through Manifold Representation Forgetting Guided by Self Mode Connectivity

• [May 2026] One paper about LLM Jailbreak defense was accepted by ICML 2026: Steering Beyond the Support: Adversarial Training on Unsupervised Jailbroken Activation Simulation

• [March 2026] I was invited as a reviewer of NIPS 2026

• [Jan 2026] I was invited as a reviewer of ICML 2026

• [Jan 2026] One paper about privacy-preserving machine unlearning was accepted by TPAMI: BlindU: Blind Machine Unlearning without Revealing Erasing Data

• [Oct 2025] I was invited as a reviewer of WWW 2026

• [Sep 2025] I was invited as a reviewer of ICLR 2026

• [Sep 2025] One paper about machine unlearning verification was accepted by TDSC: SMS: Self-supervised Model Seeding for Verification of Machine Unlearning

• [May 2025] One paper about machine unlearning evaluation was accepted by TIFS: Evaluation of Machine Unlearning Through Model Difference

• [Feb 2025] One paper about privacy protection on machine unlearning was accepted by TDSC: CRFU: Compressive Representation Forgetting Against Privacy Leakage on Machine Unlearning

• [Jan 2025] One paper about machine unlearning auditing was accepted by WWW25: TAPE: Tailored Posterior Difference for Auditing of Machine Unlearning

• [December 2024] One federated unlearning paper was accepted by TDSC: FedU: Federated Unlearning via User-Side Influence Approximation Forgetting

• [December 2024] One semantic communication unlearning paper was accepted by TIFS: SCU: An Efficient Machine Unlearning Scheme for Deep Learning Enabled Semantic Communications

• [September 2024] I was invited as a reviewer of ICLR 2025!

• [August 2024] I will join the TPC of WWW 2025!

Selected First-author Papers

1. Weiqi Wang, Zhiyi Tian, Chenhan Zhang, and Shui Yu. “BlindU: Blind Machine Unlearning without Revealing Erasing Data.” IEEE Transactions on Pattern Analysis and Machine Intelligence (2026).

2. Weiqi Wang, Chenhan Zhang, Zhiyi Tian, Shui Yu. “Machine unlearning via representation forgetting with parameter self-sharing.” IEEE Transactions on Information Forensics and Security (vol. 19, pp. 1099–1111, 2024).

3. Weiqi Wang, Zhiyi Tian, An Liu, and Shui Yu. “TAPE: Tailored Posterior Difference for Auditing of Machine Unlearning.” In Proceedings of the ACM on Web Conference 2025, pp. 3061-3072. 2025.

4. Weiqi Wang, Zhiyi Tian, Chenhan Zhang, and Shui Yu. “Scu: An efficient machine unlearning scheme for deep learning enabled semantic communications.” IEEE Transactions on Information Forensics and Security (2024).

5. Weiqi Wang, Chenhan Zhang, Zhiyi Tian, and Shui Yu. “Fedu: Federated unlearning via user-side influence approximation forgetting.” IEEE Transactions on Dependable and Secure Computing (2024).

6. Weiqi Wang, Chenhan Zhang, Zhiyi Tian, Shushu Liu, and Shui Yu. “CRFU: Compressive Representation Forgetting Against Privacy Leakage on Machine Unlearning.” IEEE Transactions on Dependable and Secure Computing (2025).

7. Weiqi Wang, Chenhan Zhang, Zhiyi Tian, Shui Yu, and Zhou Su. “Evaluation of Machine Unlearning through Model Difference.” IEEE Transactions on Information Forensics and Security (2025).

8. Weiqi Wang, Chenhan Zhang, Zhiyi Tian, and Shui Yu. “SMS: Self-supervised Model Seeding for Verification of Machine Unlearning.” IEEE Transactions on Dependable and Secure Computing (2025).

9. Weiqi Wang, Zhiyi Tian, Chenhan Zhang, An Liu, and Shui Yu. “Bfu: Bayesian federated unlearning with parameter self-sharing.” In Proceedings of the 2023 ACM Asia Conference on Computer and Communications Security, pp. 567-578. 2023.

Services

• Program Committee Member/Reviewer
  • 2026: ICML; CVPR; ACM WWW; ACM KDD; ICLR; NIPS;
  • 2025: The Web Conference(ACM WWW); ICLR;
  • 2024: The Web Conference(ACM WWW);
• Journal Reviewer
  • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
  • IEEE Transactions on Information Forensics and Security (TIFS)
  • IEEE Transactions on Dependable and Secure Computing (TDSC)
  • IEEE Transactions on Mobile Computing (TMC)
  • IEEE Transactions on Image Processing (TIP)
  • ACM Computing Surveys
  • IEEE Communications Surveys and Tutorials
  • IEEE Internet of Things Journal (IoTJ)