Backdoor in AI: Algorithms, Attacks, and Defenses

Published: | 1:47 pm | Posted in: Events

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 backdoor function within the victim model, allowing attackers to manipulate the model’s behavior using specific […]

Exploring, Counteracting and Harnessing Adversarial Examples

Published: | 4:12 pm | Posted in: Events

Speaker: Han Xu Date: Feb 12, 11:45am–12:45pm Abstract: Recently, with the development of AI and ML, their corresponding safety problems, especially their vulnerability to adversarial attacks, have also become increasingly important. In order to enhance the ML safety, it is essential to discover sound solutions for (1) identifying adversarial examples to uncover the weakness of […]

Structuring Cooperative Teams for Multi-Agent Autonomy

Published: | 4:07 pm | Posted in: Events

Speaker: Qi Zhang Date: Feb 9, 11:45am–12:45pm Abstract: Cooperative artificial intelligence (AI) equips a team of autonomous agents with the capability of planning and learning to maximize their joint utility, which finds a wide range of applications. While being a promising paradigm, current solutions to cooperative AI, instantiated as cooperative multi-agent planning and learning frameworks, […]

Learning from Imperfect Data: Incremental Learning and Few-shot Learning

Published: | 1:36 pm | Posted in: Events

Speaker: Yaoyao Liu Date: Feb 7, 11:45am–12:45pm Abstract: In recent years, artificial intelligence (AI) has achieved great success in many fields. Although impressive advances have been made, AI algorithms still suffer from an important limitation: they rely on static and large-scale datasets. In contrast, human beings naturally possess the ability to learn novel knowledge from […]

Data-Centric AI: Taming AI-ready Feature Space From Decision-Making to Generative-AI

Published: | 2:57 pm | Posted in: Events

Speaker: Dongjie Wang Date: Feb 5, 11:45am–12:45pm Abstract: Unlike humans, AI systems are brittle and not robust. They often struggle when faced with novel situations, and are highly sensitive to small perturbations, which can lead to catastrophically poor performance. These systems comprise two main components: the model and the data. In recent decades, research primarily […]

Empowering Graph Neural Networks for Real-world Tasks

Published: | 4:24 pm | Posted in: Events

Speaker: Zhichun Guo Date: Feb 2, 11:45am–12:45pm Abstract: Graph neural networks (GNNs) have been widely used on graph-structured data, but they also face a series of challenges in solving real-world problems, including scarcity of labeled data, scalability issues, and potential bias. In this talk, I will recap my research efforts in tackling these challenges and […]