Upcoming

Past

• Causal Machine Learning: Continuous Structure Learning and Identifiability of Causal Invariances

  Speaker: Kevin Bello Date: Mar 1, 11:45am–12:45pm Abstract: Interpretability and causality are key desiderata in modern machine learning systems. Graphical models, and more specifically directed acyclic graphs (DAGs, a.k.a. Bayesian networks), serve as a well-established tool for expressing interpretable causal…

• Securing Embedded Systems Using Compartmentalization

  Speaker: Arslan Khan Date: Feb 29, 11:45am–12:45pm Abstract: Embedded systems are low-power resource-constrained devices implementing specialized tasks, unlike general-purpose computers. Embedded systems find applications in various domains, from the Internet of Things (IoT) to general purpose Personal Computers (PC). Unfortunately,…

• Toward Secure Federated Learning

  Speaker: Minghong Fang Date: Feb 28, 11:45am–12:45pm Abstract: Federated learning is a distributed machine learning approach that enables multiple clients (e.g., smartphones, IoT devices, and edge devices) to collaboratively learn a model with help of a server, without sharing their…

• Security of AI-enabled Perception Systems in Autonomous Driving

  Speaker: Yi Zhu Date: Feb 27, 11:45am–12:45pm Abstract: Autonomous vehicles (AVs) are visioned as a revolutionary power for future transportation. A fundamental function of AV systems is perception, which aims to understand the surrounding driving environment using the sensors such…

• An Adversarial Perspective on the Machine Learning Pipeline

  Speaker: Fnu Suya Date: Feb 26, 11:45am–12:45pm Abstract: Machine learning models are often vulnerable to attacks during both training and test phases, yet the risks in adversarial environments are frequently misjudged. In this talk, I will first demonstrate that black-box…

• Trustworthy and Scalable Machine Learning

  Speaker: Yang Zhou Date: Feb 23, 11:45am–12:45pm Abstract: Machine learning (ML), a powerful tool for automatically extracting, managing, inferencing, and transferring knowledge, has been proven to be extremely useful in understanding the intrinsic nature of real-world big data. Despite achieving…

• From Theory to Application: Overparameterization and Machine Learning at the Edge

  Speaker: Peizhong Ju Date: Feb 21, 11:45am–12:45pm Abstract: Machine Learning (ML), a vital branch of Artificial Intelligence (AI), has seen rapid advancements in recent years. As ML continues to evolve, it faces two major challenges: the need for deeper theoretical…

• Exploring the Adversarial Robustness of Language Models

  Speaker: Muchao Ye Date: Feb 19, 11:45am–12:45pm Abstract: Language models built by deep neural networks have achieved great success in various areas of artificial intelligence, which have played an increasingly vital role in profound applications including chatbots and smart healthcare.…

• Resource-Efficient Machine Learning: Reduce the Cost of Graph Learning and Beyond

  Speaker: Xiaotian (Max) Han Date: Feb 16, 11:45am–12:45pm Abstract: In this talk, I will present my research on resource-efficient machine learning techniques for graph neural networks (GNNs) and beyond. These techniques aim to reduce the computational resources required by these…

• Backdoor in AI: Algorithms, Attacks, and Defenses

  Speaker: Ruixiang Tang Date: Feb 14, 11:45am–12:45pm Abstract: As deep learning models are increasingly integrated into critical domains, their safety emerges as a critical concern. This talk delves into the emerging threat of backdoor attacks. These attacks involve embedding a…