Skip to content

Keynotes


Toward Practical Client-Side Encryption in Cloud Computing

Robert Deng (Singapore Management University, Singapore)

Abstract: Data breaches in the cloud are on the rise and are becoming more costly to organizations each year. Client-side encryption refers to the practice of encrypting data on end users’ devices before uploading it to the cloud. This approach ensures that data is encrypted during transit and storage, making data inaccessible to anyone without the decryption keys, including service providers and other potential attackers. In this talk, we will first look at the challenges of client-side encryption and provide an overview of the key advancements as well as setbacks in addressing these challenges in the past two decades, including scalable access of encrypted data and search over encrypted data. There are numerous academic publications in this area and the choice of which techniques to use could have significant impact on the system’s security, efficiency, and usability. Finally, we will present our design and implementation of a client-side encryption system for enterprise users.

About the speaker: Robert Deng is AXA Chair Professor of Cybersecurity, Deputy Dean for Faculty & Research, School of Computing and Information Systems, Singapore Management University (SMU). His research interests are in the areas of data security and privacy, network and distributed system security, and applied cryptography. He received the Outstanding University Researcher Award from National University of Singapore, Lee Kuan Yew Fellowship for Research Excellence from SMU, and Asia-Pacific Information Security Leadership Achievements and Community Service Star from International Information Systems Security Certification Consortium (ISC2). He serves/served on the editorial boards of ACM Transactions on Privacy and Security, IEEE Security & Privacy, IEEE Transactions on Dependable and Secure Computing, IEEE Transactions on Information Forensics and Security, Journal of Computer Science and Technology, and Steering Committee Chair of the ACM Asia Conference on Computer and Communications Security. He is a Fellow of IEEE and Fellow of Academy of Engineering Singapore.

Federated Learning Security: From Dusk to Dawn

Alexandra Dmitrienko (University of Würzburg, Germany)

Abstract: The evolution of machine learning (ML) as an enabling technology has opened a new era of possibilities and applications. Among these advancements, distributed learning, specifically federated learning (FL), emerges as a significant shift in collaborative intelligence. FL’s unique ability to leverage decentralized data sources promises innovation and privacy protection for local datasets across diverse domains, including healthcare, finance, object recognition, and beyond. However, despite its potential benefits, FL has shown to be vulnerable to various threats. From poisoning attacks to adversarial perturbations and information inference, malicious actors pose significant challenges to the integrity of FL systems. Effectively addressing these vulnerabilities requires the implementation of security-by-design principles within FL frameworks. In this talk, we steer through the complex landscape of FL attacks and defenses, shedding light on the ongoing arms race between adversaries and defenders. We examine their advantages and drawbacks, gaining valuable insights into the evolving nature of these threats. We conclude by outlining research challenges and directions to enhance the resilience and security of FL systems.

About the speaker: Dr. Alexandra Dmitrienko is an esteemed Associate Professor at the University of Wuerzburg in Germany and the head of the Secure Software Systems research group. With a distinguished academic background, Dr. Dmitrienko earned her PhD in Security and Information Technology with summa cum laude distinction from TU Darmstadt in 2015. Her doctoral research focused on enhancing the security and privacy of mobile systems and applications, earning recognition from both academic consortia and industrial organizations such as the European Research Consortium for Informatics and Mathematics (ERCIM STM WG 2016 Award) and Intel (Intel Doctoral Student Honor Award, 2013). Dr. Dmitrienko’s academic journey encompasses a wealth of experience garnered from prominent security institutions in Germany and Switzerland. Prior to assuming her current faculty position in 2018, she acquired expertise at institutions including Ruhr-University Bochum (2008-2011), Fraunhofer Institute for Information Security in Darmstadt (2011-2015), and ETH Zurich (2016-2017). Throughout her career, Dr. Dmitrienko’s research interests have spanned diverse domains within cybersecurity, including software security, systems security and privacy, and the security and privacy of mobile, cyber-physical, and distributed systems. Today, her research also largely focuses on security and privacy aspects of Machine Learning methods.

XiaoFeng Wang (Indiana University at Bloomington, USA)


 Alvaro Cardenas (University of California, Santa Cruz, USA)
 Michail Maniatakos (New York University Abu Dhabi, UAE)