Jiaming Zhang (张家明) is currently a Postdoctoral Research Fellow at Nanyang Technological University (NTU), working with Prof. Wei Yang Bryan Lim. Prior to this, I was a postdoc at Hong Kong University of Science and Technology (HKUST), working with Prof. Dit-Yan Yeung. I received my Ph.D. from Beijing Jiaotong University (BJTU) under the supervision of Prof. Jitao Sang.

My research focuses on Trustworthy AI, with particular interests in adversarial robustness and privacy-preserving machine learning. Recently, I have been exploring these topics in the context of Multimodal Large Language Models (MLLMs).

🔥 News

• 2025.11: I gave an invited talk on “Security and Privacy on Modern MLLMs” at Institute of Science Tokyo, Japan.
• 2025.09: Our survey paper “Safety at Scale” is published in Foundations and Trends® in Privacy and Security.
• 2025.08: One paper is accepted by TIFS 2025.
• 2025.06: I joined NTU as a Research Fellow.
• 2025.03: One paper is accepted by ACL 2025 Findings.
• 2025.02: Two papers are accepted by CVPR 2025.

📝 Selected Publications

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety
Xingjun Ma, Yifeng Gao, Yixu Wang, … Jiaming Zhang, …, Yu-Gang Jiang
Foundations and Trends® in Privacy and Security 2025   [Paper]   [ArXiv]

Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models
Jiaming Zhang, Junhong Ye, Xingjun Ma, Yige Li, Yunfan Yang, Yunhao Chen, Jitao Sang, Dit-Yan Yeung
CVPR 2025   [Paper]   [Code]   [Project Page]

TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models
Xin Wang, Kai Chen, Jiaming Zhang, Jingjing Chen, Xingjun Ma
CVPR 2025   [Paper]

Investigating and Enhancing Vision-Audio Capability in Omnimodal Large Language Models
Rui Hu, Delai Qiu, Shuyu Wei, Jiaming Zhang, Yining Wang, Shengping Liu, Jitao Sang
ACL Findings 2025   [Paper]

MF-CLIP: Leveraging CLIP as Surrogate Models for No-box Adversarial Attacks
Jiaming Zhang, Lingyu Qiu, Qi Yi, Yige Li, Jitao Sang, Changsheng Xu, Dit-Yan Yeung
TIFS 2025   [Paper]   [Code]

Adversarial Prompt Tuning for Vision-Language Models
Jiaming Zhang, Xingjun Ma, Xin Wang, Lingyu Qiu, Jiaqi Wang, Yu-Gang Jiang, Jitao Sang
ECCV 2024   [Paper]   [Code]

Unlearnable Clusters: Towards Label-agnostic Unlearnable Examples
Jiaming Zhang, Xingjun Ma, Qi Yi, Jitao Sang, Yu-Gang Jiang, Yaowei Wang, Changsheng Xu
CVPR 2023   [Paper]   [Code]

ImageNet Pre-training also Transfers Non-robustness
Jiaming Zhang, Jitao Sang, Qi Yi, Yunfan Yang, Huiwen Dong, Jian Yu
AAAI 2023   [Paper]   [Code]

Low-mid Adversarial Perturbation against Unauthorized Face Recognition System
Jiaming Zhang, Qi Yi, Dongyuan Lu, Jitao Sang
Information Sciences 2023   [Paper]

Towards Adversarial Attack on Vision-Language Pre-training Models
Jiaming Zhang, Qi Yi, Jitao Sang
ACM MM 2022   [Paper]   [Code]

Benign adversarial attack: Tricking algorithm for goodness
Jitao Sang, Xian Zhao, Jiaming Zhang, Zhiyu Lin
ACM MM 2022   [Paper]

Robust CAPTCHAs towards malicious OCR
Jiaming Zhang, Jitao Sang, Kaiyuan Xu, Shangxi Wu, Xian Zhao, Yanfeng Sun, Yongli Hu, Jian Yu
TMM 2021   [Paper]

Adversarial privacy-preserving filter
Jiaming Zhang, Jitao Sang, Xian Zhao, Xiaowen Huang, Yanfeng Sun, Yongli Hu
ACM MM 2020   [Paper]   [Code]

🥇 Honors and Awards

• 2024: ACM China Doctoral Dissertation Award Nominee (Top 5 in China)
• 2024: SIGMM China Doctoral Dissertation Award
• 2023: Zhixing Award (校长奖学金) Nominee
• 2022: China PhD National Scholarship (博士研究生国家奖学金)
• 2022: Rank #1 (1/178) in AISC 2022 Facial Recognition Security Track

💬 Invited Talks

• Nov 2025: Security and Privacy on Modern MLLMs, Institute of Science Tokyo, Tokyo, Japan.
• Apr 2025: Trustworthy AI - Adversarial Attacks & Robustness, Nanyang Technological University, Singapore.
• Oct 2021: Trustworthy Multimedia Analysis, ACM MM 2021 Tutorial, Chengdu, China.

🌟 Academic Services

• Journal Reviewer: TPAMI, TIP, TMLR, TCSVT, TIST
• Conference PC Member: NeurIPS, ICLR, ICML, CVPR, ICCV, ECCV, ACM MM, AAAI, IJCAI