Workshop on Security and Privacy in Standardized IoT (SDIoTSec) 2024 Program

IoT technologies bridge domains to create innovative solutions, but this can shift trust balances and strain cybersecurity and privacy. Since humans are commonly the beneficiaries or targets of IoT systems, concerns about privacy (and safety) may be heightened. Also, IoT can both have more sensitive position in a network and fewer power, computing, etc. resources than other equipment (i.e., is constrained). Towards solving these challenges, IoT can leverage existing standards, but new standards are needed for at least some cases. Of course, cybersecurity and privacy management is technology agnostic and standards for these domains certain apply to IoT, but especially for the cybersecurity practitioner, realities of IoT (e.g., constraints) can break expectations built into the standards or how they are generally understood and used. Today, standards and national efforts around cybersecurity and privacy of IoT abound. Notable examples in the United States are the Cybersecurity Improvement Act and CyberTrust Mark cybersecurity labeling program for consumer IoT. Globally, multiple nations are exploring their own labeling programs, including, but not limited to Singapore and Japan. In the European Union, efforts are underway to ensure the cybersecurity of IoT products via the Cyber Resiliency Act. In the standards space, we can look to solutions from IETF for device intent signaling and device on-boarding, among other topics and efforts such as 27400 series from ISO. These efforts are welcome since IoT adoption depends on delivering solutions that preserve cybersecurity and privacy. Research and then standards can help bridge these gaps and inform efforts to raise the bar of cybersecurity and privacy for IoT across all sectors since doing so can motivate trust in and adoption of the technology.

Speaker's Biography: Michael Fagan is a Computer Scientist and Technical Lead with the Cybersecurity for IoT Program which aims to develop guidance towards improving the cybersecurity of IoT devices and systems. The program works within the National Institute of Standards and Technology’s Information Technology Laboratory (ITL) and supports the development and application of standards, guidelines, and related tools to improve the cybersecurity of IoT systems, products, connected devices and the environments in which they are deployed. By collaborating with stakeholders across government, industry, international bodies, academia, and consumers, the program aims to cultivate trust and foster an environment that enables innovation on a global scale. Michael leads work exploring IoT cybersecurity in specific sectors or use cases, such as enterprise systems, the federal government, and consumer home networks. He holds a Ph.D. in Computer Science & Engineering.

I present the results of an architectural risk analysis (ARA) of large language models (LLMs), guided by an understanding of standard machine learning (ML) risks previously identified by BIML in 2020. After a brief level-set, I cover the top 10 LLM risks, then detail 23 black box LLM foundation model risks screaming out for regulation, finally providing a bird’s eye view of all 81 LLM risks BIML identified. BIML’s first work, published in January 2020 presented an in-depth ARA of a generic machine learning process model, identifying 78 risks. In this talk, I consider a more specific type of machine learning use case—large language models—and report the results of a detailed ARA of LLMs. This ARA serves two purposes: 1) it shows how our original BIML-78 can be adapted to a more particular ML use case, and 2) it provides a detailed accounting of LLM risks. At BIML, we are interested in “building security in” to ML systems from a security engineering perspective. Securing a modern LLM system (even if what’s under scrutiny is only an application involving LLM technology) must involve diving into the engineering and design of the specific LLM system itself. This ARA is intended to make that kind of detailed work easier and more consistent by providing a baseline and a set of risks to consider.

Speaker's Biography: Gary McGraw is co-founder of the Berryville Institute of Machine Learning where his work focuses on machine learning security. He is a globally recognized authority on software security and the author of eight best selling books on this topic. His titles include Software Security, Exploiting Software, Building Secure Software, Java Security, Exploiting Online Games, and 6 other books; and he is editor of the Addison-Wesley Software Security series. Dr. McGraw has also written over 100 peer-reviewed scientific publications. Gary serves on the Advisory Boards of Calypso AI, Legit, Irius Risk, Maxmyinterest, and Red Sift. He has also served as a Board member of Cigital and Codiscope (acquired by Synopsys) and as Advisor to CodeDX (acquired by Synopsys), Black Duck (acquired by Synopsys), Dasient (acquired by Twitter), Fortify Software (acquired by HP), and Invotas (acquired by FireEye). Gary produced the monthly Silver Bullet Security Podcast for IEEE Security & Privacy magazine for thirteen years. His dual PhD is in Cognitive Science and Computer Science from Indiana University where he serves on the Dean’s Advisory Council for the Luddy School of Informatics, Computing, and Engineering.