Jing Wu

Jing Wu

Associate Professor

Tianjin University

Research Interests

Trustworthy Machine Learning
Safety Alignment
Machine Unlearning
Adversarial Attacks & Defenses

About

I joined Tianjin University as an Associate Professor in June 2026. I was a Postodoctoral Research Fellow at Department of Data Science & AI, Monash University, working closely with A/Prof. Mehrtash Harandi, Prof. Dinh Phung, Prof.Jianfei Cai and Dr. Trung Le. I obtained my Ph.D.from Monash University, where I have the privilege of being mentored by A/Prof. Mehrtash Harandi and Dr. Munawar Hayat. Before joining Monash University, I was a master's student at UESTC, where I worked with Prof. Yipeng Liu and Prof. Ce Zhu.

Selected Publications

View All →

Perceptual Alignment Reveals Vulnerability in Unlearned Diffusion Models

Jing Wu, Trung Le, Mingyi Zhou, Dinh Phung, Jianfei Cai, Mehrtash Harandi

34th ACM International Conference on Multimedia (ACM MM 2026)

pH-Strips for Selective Forgetting: A Blunt but Fast Diagnostic Baseline for Machine Unlearning

Chengyao Qian, Jing Wu†, Trung Le, Dinh Phung, Mehrtash Harandi

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2026)

Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient Influence

Quoc Minh Nguyen, Trung Le, Jing Wu, Anh Tuan Bui, Mehrtash Harandi

International Conference on Representation Learning (ICLR 2026)

DIET: Machine Unlearning on a Data-Diet

Nilakshan Kunananthaseelan, Jing Wu, Le Trung, Gholamreza Haffari, Mehrtash Harandi

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2026)

Oral Presentation

MUNBa: Machine Unlearning via Nash Bargaining

Jing Wu, Mehrtash Harandi

Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV 2025)

News

2026-07

Our new paper "Perceptual Alignment Reveals Vulnerability in Unlearned Diffusion Models" got accepted by ACM MM 2026!🎉