Trustworthy Machine Learning

Nominated computer vision tasks have nowadays performed on super-human level with the advances of deep learning techniques. However, adversarial machine learning researchers demonstrate that such vision systems could not yet be as robust as human systems. Acting as a new gamut of technologies, trustworthy machine learning covers the research and development of studying the intact capabilities and malicious behaviors of machine learning models in an adversarial scenario. The potential vulnerabilities of ML models to malicious attacks can result in severe consequences for safety-critical systems. One most known manner is via imperceptible perturbations to the input images/videos. Although it is not to be alarmist, researchers in machine learning and computer vision areas have a responsibility to preempt attacks and build safeguards especially when the task is critical for information security, and human lives (e.g., autonomous driving systems). We need to deepen our understanding of machine learning in adversarial environments.

While the negative implications of this nascent technology for computer vision have been widely discussed, researchers are yet to explore their positive opportunities in numerous aspects. Positive impacts of trustworthy machine learning are not limited to boost the robustness of ML models, but cut across several other domains including privacy protection, reliability and safety test, model understanding, improving generalisation performance in computer vision from different perspectives, etc.}

Since there are both positive and negative aspects of computer vision systems, addressing trustworthy machine learning to their use in such scenario in the right direction requires a framework to embrace the positives. This workshop aims to bring together researchers and practitioners from a variety of communities (e.g., computer vision, machine learning, and computer security) in an effort to synthesize promising ideas and research directions, as well as foster and strengthen cross-community collaborations on both theoretical studies and practical applications for advanced vision systems.

All the papers should be submitted using Easychair website: https://easychair.org/conferences/?conf=tmlavs24.

At least one author of each accepted paper must register to present the work on-site in Hanoi, Vietnam, as scheduled in the conference program.

Accepted papers will be included in the companion proceedings of ACCV 2024. Selected high quality papers will be recommended for publication at high-impact international journals such as IEEE trans, after further extensions and revisions.

We welcome submission from different aspects of trustworthy ML for computer vision systems, including but not limited to:

Paper submission deadline:	August 28th, 2024
Notification to Authors:	September 20th, 2024
Registration:	TBD
Conference date:	October 11st, 2024