Ping Guo

Postdoctoral Fellow

Department of Computer Science

City University of Hong Kong

Hong Kong SAR, China

I am a Postdoctoral Fellow in the CS Department at City University of Hong Kong, advised by Prof. Qingfu Zhang (Chair Professor, IEEE Fellow).

My research focuses on computational intelligence approaches to build advanced AI systems. Specifically, I develop evolutionary computation methods and machine learning algorithms for solving complex optimization problems in real-world applications.

Research Interests:

Evolutionary Computation & Multi-objective Optimization
Adversarial Machine Learning & Robustness
Large Language Models for Algorithm Design
Computational Intelligence Applications

Academic Impact: across multiple publications, with an h-index of 5.

Throughout my academic journey, I have had the privilege of collaborating with distinguished researchers: Prof. Qingchuan Zhao, Dr. Xi Lin, and Mr. Cheng Gong.

I serve as a reviewer for top-tier conferences including NIPS, ICML, ICLR, AISTATS, and CEC, as well as journals such as Swarm and Evolutionary Computation and Evolutionary Computation.

news

Mar 01, 2025	🎉 Our paper “MOS-Attack: A Scalable Multi-objective Adversarial Attack Framework” has been accepted by CVPR 2025! [Paper] [CVPR]
Dec 01, 2024	📄 New preprint available: “CoEvo: Continual Evolution of Symbolic Solutions Using Large Language Models” [ArXiv]
Nov 01, 2024	🎉 Our paper “Exploring the Adversarial Frontier: Quantifying Robustness via Adversarial Hypervolume” has been accepted by IEEE TETCI! [Paper] [IEEE]

selected publications

CVPR
MOS-Attack: A Scalable Multi-Objective Adversarial Attack Framework

Ping Guo, Cheng Gong, Xi Lin, and 4 more authors

In 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2025

Abs DOI Bib HTML Code

Crafting adversarial examples is crucial for evaluating and enhancing the robustness of Deep Neural Networks (DNNs), presenting a challenge equivalent to maximizing a non-differentiable 0-1 loss function. However, existing single objective methods, namely adversarial attacks focus on a surrogate loss function, do not fully harness the benefits of engaging multiple loss functions, as a result of insufficient understanding of their synergistic and conflicting nature. To overcome these limitations, we propose the Multi-Objective Set-Based Attack (MOS Attack), a novel adversarial attack framework leveraging multiple loss functions and automatically uncovering their interrelations. The MOS Attack adopts a set-based multi-objective optimization strategy, enabling the incorporation of numerous loss functions without additional parameters. It also automatically mines synergistic patterns among various losses, facilitating the generation of potent adversarial attacks with fewer objectives. Extensive experiments have shown that our MOS Attack outperforms single-objective attacks. Furthermore, by harnessing the identified synergistic patterns, MOS Attack continues to show superior results with a reduced number of loss functions.
@inproceedings{guo2025mos, address = {Los Alamitos, CA, USA}, author = {Guo, Ping and Gong, Cheng and Lin, Xi and Liu, Fei and Lu, Zhichao and Zhang, Qingfu and Wang, Zhenkun}, booktitle = {2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, dimensions = {true}, doi = {10.1109/CVPR52734.2025.00475}, keywords = {Computer vision, Codes, Artificial neural networks, Robustness, Adversarial machine learning, Pattern recognition, Optimization}, month = jun, pages = {5041-5051}, publisher = {IEEE Computer Society}, title = {MOS-Attack: A Scalable Multi-Objective Adversarial Attack Framework}, year = {2025} }