As AI continues to play a critical role in real-world applications, its security and trustworthiness are becoming increasingly important. While technical capabilities have advanced rapidly, research on the security and robustness of AI systems has not kept pace. Recent studies have highlighted vulnerabilities, especially in adversarial environments where attackers can manipulate input data to deceive AI systems. Traditional AI methods, which often overlook these threats, may suffer significant performance degradation under such conditions.

This workshop aims to bring together researchers and practitioners to address these challenges. The program will consist of two parts:
We welcome research paper submissions on all aspects of AI security. This is an opportunity to share your work, insights, and findings with fellow researchers and industry experts.

• Submission Deadline: May 10, 2025
• Submission Link: https://www.icmlc.com/submission/icmlc

(Please submit under the “Adversarial Machine Learning” track)

Topics of interest include, but are not limited to:

• Adversarial attack and defense techniques
• Data sanitization and anomaly detection
• Vulnerability assessment and robust learning
• Adversarial examples and generative adversarial networks (GANs)
• Security risks of large language models (LLMs)
• Real-world applications and case studies

This panel discussion will focus on the growing concern over the misuse and manipulation of Large Language Models (LLMs) such as ChatGPT. As these tools are integrated into everyday life, it is essential to examine the risks of generating harmful or misleading content and to explore ways to mitigate them.

The panel will feature experts from academia, industry, and policy, addressing practical challenges and offering perspectives on building more secure, reliable, and human-aligned AI systems. All participants are welcome to join the open-floor discussion.

• Robert J. Marks, Bayor University, USA
• Peng Shi, The University of Adelaide, Australia
• Kevin Wong, Murdoch University, Australia
• Battista Baggio, University of Cagliari, Italy
• Patrick Chan, South China University of Technology, China

Please contact Dr. Patrick Chan