Keynote Speakers

Toward Open, Programmable, Intelligent, and Secure AI-RAN


This keynote explores how openness, programmability, and intelligence can restart the innovation cycle in mobile networks. Despite the advances brought by 5G, a growing gap separates research from real-world products and deployments. Beyond business and market factors, technical barriers also slow innovation: an inflexible RAN that is hard to deploy, adapt, upgrade, and secure; manual control and tuning that widens the gap between theoretical and practical performance; and limited automation in network management. This keynote highlights the transformative potential of moving from conventional networks to open, programmable, and intelligent systems. It examines the challenges of securing three elements (the network infrastructure and software, the intelligence, and the open interfaces) and then shows how that same openness, intelligence, and softwarization can make networks more secure and resilient. First, data exposure enables anomaly detection and RAN regression testing. Second, generative AI and open software enable automation and workflows for synthesizing, testing, and hardening RAN software. By reframing openness not as a security liability but as a foundation for resilience, this keynote argues that the path to more secure mobile networks runs directly through the same principles driving the next wave of Open and AI-RAN innovation.

Michele Polese
Northeastern University, Boston, USA

Michele Polese is a Research Assistant Professor at the Institute for Intelligent Networked Systems, Northeastern University, Boston, since October 2023. He is also the chair for the AI-and-RAN working group of the AI-RAN Alliance and a co-founder at zTouch Networks, Inc. He received his Ph.D. at the Department of Information Engineering of the University of Padova in 2020. He then joined Northeastern University as a research scientist and part-time lecturer in 2020. During his Ph.D., he visited New York University (NYU), AT&T Labs in Bedminster, NJ, and Northeastern University. His research interests are in the end-to-end design and testing of open, programmable, intelligent, and secure next-generation cellular networks, including Open RAN, AI-RAN, and 6G. He is also interested in spectrum sharing, experimental wireless research and open-source software, millimeter-wave and terahertz networks, and the performance evaluation of end-to-end, complex networks. He has contributed to O-RAN technical specifications and submitted responses to multiple FCC and NTIA notice of inquiry and requests for comments, and is a member of the Committee on Radio Frequency Allocations of the American Meteorological Society (2022-2027). He is PI and co-PI in research projects on 6G funded by the NTIA, the O-RAN ALLIANCE, U.S. NSF, OUSD, and MassTechCollaborative, and was awarded with several best paper awards and the 2022 Mario Gerla Award for Research in Computer Science. Michele is an editor for the IEEE Transactions on Mobile Computing, IEEE Communications Magazine, and Computer Networks, and has served as guest editor for a JSAC Special Issue on Open RAN. He was TPC co-chair of European Wireless 2025, WONS 2024, WiNTECH 2024, and WNS3 2021-2022, among others, and he has organized multiple events (Open6G+AI Workshop, IEEE RitiRAN) around open and programmable networks. Michele holds multiple patents around Open RAN/cellular networks, and led the establishment of the Open6G testing center at Northeastern.

Small Steps, Big Systems: LLMs and the Scale Problem in Wireless Protocol Security


Wireless protocol security from Bluetooth to 5G basebands has long been an intractably large problem space, addressed piecemeal: one manual standard analysis, one fuzzing campaign, one rehosted firmware at a time. This talk surveys an emerging shift, where large language models are being applied across the full protocol lifecycle to extract formal models from ambiguous specification text, generate test grammars and state machines for fuzzing, and assist reverse engineering of proprietary baseband implementations. This shift allows to take bigger steps where progress was previously bottlenecked by scarce expert effort. Drawing on the speaker’s own work on Bluetooth standard analysis and firmware rehosting alongside recent results from the community, the talk asks whether LLMs act as genuine force multipliers for tackling more complete systems, or whether they merely speed up the same small steps.

Nils Ole Tippenhauer
CISPA Helmholtz Center for Information Security, Saarbrücken, Germany

Nils Ole Tippenhauer is a faculty member at the CISPA Helmholtz Center for Information Security in Saarbrücken, Germany, where he heads the SCy-Phy research group. He earned his Dr. Sc. in Computer Science from ETH Zurich in 2012, working in the System Security group of Prof. Srdjan Čapkun, and holds a Dipl.-Ing. in Computer Engineering from the Hamburg University of Technology. Before joining CISPA in 2018, he was an Assistant Professor at the Singapore University of Technology and Design (SUTD). His research spans wireless security, cyber-physical systems and industrial control system security, and embedded firmware analysis, with notable work on GPS spoofing, Bluetooth standard vulnerabilities (including KNOB and BLURtooth), distance bounding, and automated firmware rehosting. He is General Chair of ACM WiSec 2026, and has previously served the community as TPC Chair and in various organizational roles for venues including AsiaCCS and WiSec.