Description

The nexus between artificial intelligence (AI) and big data analytics is digitally transforming many industries by deploying intelligence systems in real-time, including healthcare, finance, robotics, and transportation. Designing and deploying algorithms that are reliable, robust, and secure is desirable for trustworthy systems with high-stakes decision making. For instance, AI-assisted robotic surgery, automated financial trading, autonomous driving and many more modern applications are vulnerable to concept drifts, dataset shifts, misspecifications, perturbations, and adversarial attacks beyond human or even machine comprehension level, thereby posing dangerous threats to various stakeholders at different levels. Moreover, building trustworthy AI systems requires lots of research efforts in addressing different mechanisms and approaches that could enhance user and public trust. To name a few, following topics are known to be topic of interests in Trustworthy AI, but not limited to: (i) bias and fairness, (ii) explainability, (iii) robust mitigation of adversarial attacks, (iv) improved privacy and security in model building, (v) being decent, and (vi) model attribution. All of these topics are important and need to be addressed.

This special session aims to draw together state-of-the-art advances in machine learning (ML) to address challenges for ensuring reliability in trustworthy systems. The challenges in different learning paradigms are including, but not limited to (1) robust learning, (2) adversarial learning, (3) stochastic, deterministic and non-deterministic learning. Nonetheless, all aspects of learning algorithms that can deal with reliable & robust issues are the focus of the special session. It will focus on robustness and performance guarantee, as well as, consistency, transparency and safety of AI which is vital to ensure reliability. The special session will attract analytics experts to build trustworthy AI systems by developing and assessing theoretical and empirical methods, practical applications, and new ideas and identify directions for future studies. Original contributions as well as comparative studies among different methods are welcome with unbiased literature review.

Topics of Interest

Topics of the special session include (with reliable/robustness/secure learning methods), including but not limited to:

• Robustness of machine learning/deep learning/reinforcement learning algorithms and trustworthy systems in general.

• Confidence, consistency, and uncertainty in model predictions for reliability beyond robustness.

• Transparent AI concepts in data collection, model development, deployment, and reporting.

• Adversarial attacks – evasion, poisoning, extraction, and inference.

• New solutions to make a system robust to novel or potentially adversarial inputs; to handle model mis-specification, corrupted training data, addressing concept drifts, or dataset shifts.

• Theoretical and empirical analysis of reliable/robust/secure ML methods.

• Comparative studies with competing methods without reliable/robust certified properties.

• Applications of reliable/robust machine learning algorithms in domains such as biomedical, finance, computer vision, natural language processing, big data, and all other relevant areas.

• Unique societal and legal challenges facing reliability for trustworthy AI systems.

Looking forward to meeting you at the event!!!