AAAI 2023technical0 citations
AAAI New Faculty Highlights: General and Scalable Optimization for Robust AI
Abstract
Deep neural networks (DNNs) can easily be manipulated (by an adversary) to output drastically different predictions and can be done so in a controlled and directed way. This process is known as adversarial attack and is considered one of the major hurdles in using DNNs in high-stakes and real-world applications. Although developing methods to secure DNNs against adversaries is now a primary research focus, it suffers from limitations such as lack of optimization generality and lack of optimization scalability. My research highlights will offer a holistic understanding of optimization foundations for robust AI, peer into their emerging challenges, and present recent solutions developed by my research group.
BibTeX
@article{Liu_2024, title={AAAI New Faculty Highlights: General and Scalable Optimization for Robust AI}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/26814}, DOI={10.1609/aaai.v37i13.26814}, abstractNote={Deep neural networks (DNNs) can easily be manipulated (by an adversary) to output drastically different predictions and can be done so in a controlled and directed way. This process is known as adversarial attack and is considered one of the major hurdles in using DNNs in high-stakes and real-world applications. Although developing methods to secure DNNs against adversaries is now a primary research focus, it suffers from limitations such as lack of optimization generality and lack of optimization scalability. My research highlights will offer a holistic understanding of optimization foundations for robust AI, peer into their emerging challenges, and present recent solutions developed by my research group.}, number={13}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Liu, Sijia}, year={2024}, month={Jul.}, pages={15447-15447} }