Conference: Workshop on LLM for Network Security

The project aims to bring together experts from diverse disciplines to explore recent advances in foundation models and large language models (LLMs) and their pivotal roles in shaping the future of network security technologies. Recent breakthroughs in artificial intelligence demonstrate significant potential in various domains of cybersecurity, including malware detection, software testing, forensic analysis, trust evaluation, and automated defense. The workshop is envisioned as a hub for interdisciplinary discourse and collaboration, creating a forward-thinking research agenda. It will delve into three key domains: LLM applications, network operations, and the human dimension of cybersecurity, addressing urgent topics such as trust, ethics, and the combating of misinformation. Given the evolving threats and growing inter-connectivity of networks, the integration of AI and cybersecurity technologies is paramount for national security. To this end, there is a need to actively involve a multidisciplinary community to devise innovative solutions to emerging challenges. The workshop aims to catalyze vibrant discussions, with participants presenting cutting-edge research and engaging in substantive dialogues about the opportunities and obstacles in their respective fields. The organizers will produce a comprehensive report summarizing the foundations and challenges of foundation models/LLM and their applications to network security. This report will align the advances in AI with practical security applications and outline a roadmap for future AI research in cybersecurity. Through collaboration and knowledge exchange, this workshop seeks to provide stakeholders with actionable insights to reshape the trajectory of network security research, facilitate the development of resilient defenses, and promote a sustainable digital ecosystem. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.