In conjunction with ACM Conference on Mobile Computing and Networking (MobiCom) 2024
Machine learning (ML) has become a potent tool in the domain of wireless networks, addressing complex tasks across Edge computing, IoT, embedded systems, and NextG networks. Enhancing the performance of ML-based wireless systems is paramount in their design. Recent research has highlighted the effectiveness of adversarial ML (AML) techniques in compromising such systems, emphasizing the need for a deeper understanding of AML's impact on wireless technologies. Therefore, developing efficient and robust ML algorithms for wireless security is crucial, particularly ones that can operate effectively with limited power and computational resources. In response to these challenges, our workshop aims to bring together experts from the ML, privacy, security, wireless communications, and networking fields globally. This platform facilitates the dissemination of cutting-edge research findings in these critical areas, encouraging the exchange of ideas and fostering research collaborations to drive innovation forward.
Scope and background: Machine learning (ML) has become a potent tool in the domain of wireless networks, addressing complex tasks across Edge computing, IoT, embedded systems, and NextG networks. Enhancing the performance of ML-based wireless systems is paramount in their design. Recent research has highlighted the potential of ML techniques in optimizing various aspects of wireless communications, from spectrum management to resource allocation. In addition, it is important to utilize the power of ML solutions to secure wireless communications against adversaries. Therefore, developing efficient and robust ML algorithms for wireless communications is crucial, particularly ones that can operate effectively with limited power and computational resources. In response to these challenges, our workshop aims to bring together experts from the ML, wireless communications, networking, and security fields globally. This platform facilitates the dissemination of cutting-edge research findings in these critical areas, encouraging the exchange of ideas and fostering research collaborations to drive innovation forward.
Topics of Interest (but not limited to):
Submission Guidelines: Workshop submissions are required to be in English and formatted according to the standard ACM conference style, with a strict limit of six pages. Accepted papers will be published in the conference proceedings and the ACM digital library. Please note that only PDF files will be considered for the review process. All submissions must be thoroughly anonymized for double-blind reviewing.
Submission Website: https://mlnextg24.hotcrp.com/
Paper submission due: July 19, 2024 August 23, 2024
Notification to authors: August 23, 2024 September 13, 2024
Camera ready due: September 13, 2024 October 11, 2024
Workshop date: November 18, 2024
Machine Learning (ML) has revolutionized the landscape of wireless networks, driving advancements in Edge computing, IoT, and NextG networks. However, as ML applications grow in complexity and scale, so do the security threats posed by adversarial Machine Learning (AML). AML techniques have proven capable of undermining ML-based wireless systems, raising critical concerns about their reliability and security.
This talk delves into the intersection of ML and network security, with a focus on developing robust and efficient ML algorithms tailored for resource-constrained environments. We will explore the vulnerabilities of current ML models in NextG networks, the impact of AML in NextG, and emerging strategies to mitigate these threats. By fostering a deeper understanding of these challenges, we aim to pave the way for designing trustworthy ML systems that can withstand adversarial attacks and ensure the secure operation of next-generation wireless networks.
