Large Language Models For Social Good and Secure Code: Opportunities and Challenge

The rapid evolution of large language models (LLMs) has unlocked transformative potential across domains that directly impact society. This talk will first explore how LLMs can be leveraged for AI for Social Good— enabling meaningful advancements in public welfare and safety. I will highlight ongoing efforts and research directions in harnessing LLMs to combat online abuse, foster healthier digital interactions, and create safer gaming environments for children. In the second part, I will shift focus to LLMs and Code Security, discussing the dual role of LLMs in both improving and threatening software security. Specifically, I will present recent progress in strengthening LLM-based code generation for security assurance and advancing LLM-driven vulnerability detection and repair. Together, these topics illustrate how the responsible development of LLMs can contribute not only to social good but also to the foundation of a more secure digital ecosystem. 

Hongxin Hu is a Professor and Associate Chair of the Department of Computer Science and Engineering at University at Buffalo, SUNY. He is a recipient of the NSF CAREER Award (2019) and Amazon Research Award (2022). His research spans security, machine learning, and networking. He has participated in multiple cross-university, cross-disciplinary projects funded by NSF. His research has also been funded by NSA, USDOT, Google, VMware, Amazon, etc. He has published over 150 refereed technical papers, many of which appeared in top-tier conferences such as S&P, CCS, USENIX Security, NDSS, SIGCOMM, NSDI, NeurIPS, ICML, and CHI, and well-recognized journals such as IEEE TIFS, IEEE TDSC, IEEE/ACM TON, and IEEE TKDE. He is the recipient of IEEE Big Data Security Senior Research Award in 2025, ACM SACMAT Test-of-Time Award in 2024, and the Best Paper Awards from ACM ASIACCS (2022), ACSAC (2020), IEEE ICC (2020), ACM SIGCSE (2018), and ACM CODASPY (2014). His research has won the First Place Award in ACM SIGCOMM 2018 SRC. His research has also been featured by the IEEE Special Technical Community on Social Networking and received 50+ press coverage including ACM TechNews, InformationWeek, Slashdot, etc