The Internet of Things (IoT) has become increasingly popular and innovative. With the rise of connected devices, we have an opportunity to significantly improve the safety of legacy systems. For instance, insights from data across systems can be exploited to reduce accidents, improve air quality and support disaster events. IoT based cyber-physical systems (CPS) also bring new risks that arise due to the unexpected interaction between systems and the larger number of attack vectors on these systems. These safety risks can arise in the context of use of medical devices, smart home appliance control, smart car design or conflicts in policy execution at a societal scale.

The Internet of Safe Things workshop seeks to bring together researchers to create solutions for the development of safe cyber-physical systems. As safety is inherently linked with the security and privacy of a system, we also seek contributions in these areas that address safety concerns. We seek to develop a community that systematically dissects the vulnerabilities and risks exposed by these emerging CPSes, and creates tools, algorithms, frameworks, and systems that help in the development of safe systems.

We seek contributions across domains - autonomous vehicles, smart homes, medical devices, smart grid; and across disciplines - systems, control, human-computer interaction, security, reliability, machine learning, and verification.

Program anchor

---

Program

All times are in PDT (UTC-8)

Keynote anchor

---

Keynote

Semantic Adversarial Analysis for Verified AI-Based Autonomy

Abstract: Verified artificial intelligence (AI) is the goal of designing AI-based systems that have strong, verified assurances of correctness with respect to mathematically-specified requirements. This goal is particularly important for autonomous and semi-autonomous systems. In this talk, I will discuss the importance of formal modeling of the environment and context of AI-based autonomous systems in analyzing their safety and security. This approach, termed "semantic adversarial analysis", blends ideas from formal methods, adversarial machine learning, and simulation-based testing for the design and analysis of AI-based autonomous systems. I will discuss semantic adversarial analysis using examples from the domain of intelligent cyber-physical systems, with a particular focus on autonomous vehicles and aerospace systems.

Bestpaper anchor

---

Best Paper Award

Egocentric Abstractions for Verification of Distributed Cyber-Physical Systems
Sung Woo Jeon and Sayan Mitra (University of Illinois at Urbana-Champaign)

cfp anchor

---

Important Dates

Paper/Demo Submission Deadline	January 25th, 2021 (AoE, UTC-12) January 29th, 2021 (AoE, UTC-12)
Acceptance Notification	February 25th, 2021
Camera-ready Submission Deadline	March 5th, 2021 (AoE, UTC-12) March 25th, 2021 (AoE, UTC-12)
Workshop	May 27th, 2021

---

Call for Papers

As traditionally segregated systems are brought online for next-generation connected applications, we have an opportunity to significantly improve the safety of legacy systems. For instance, insights from data across systems can be exploited to reduce accidents, improve air quality and support disaster events. Cyber-physical systems (CPS) also bring new risks that arise due to the unexpected interaction between systems. These safety risks arise because of information that distracts users while driving, software errors in medical devices, corner cases in data-driven control, compromised sensors in drones or conflicts in societal policies. Accordingly, the Workshop on the Internet of Safe Things (or SafeThings, for brevity) seeks to bring researchers and practitioners that are actively exploring system design, modeling, verification, authentication approaches to provide safety guarantees in the Internet of Things (IoT). The workshop welcomes contributions that integrate hardware and software systems provided by disparate vendors, particularly those that have humans in the loop. As safety is inherently linked with security and privacy, we also seek contributions in these areas that address safety concerns. With the SafeThings workshop, we seek to develop a community that systematically dissects the vulnerabilities and risks exposed by these emerging CPSes, and create tools, algorithms, frameworks, and systems that help in the development of safe systems.

The scope of SafeThings includes safety topics as it relates to an individual’s health (physical, mental), society (air pollution, toxicity, disaster events), or the environment (species preservation, global warming, oil spills). The workshop considers safety from a human perspective, and thus, does not include topics such as thread safety or memory safety in its scope.

Topics of interest include, but are not limited to, the following categories:

• Verification of safety in IoT/CPS platforms
• Authentication in IoT/CPS settings
• Adversarial machine learning and testing of IoT/CPS systems
• Secure perception, localization, and planning in autonomous systems (e.g., autonomous vehicles and drones)
• Sensors/analog and network protocol security in IoT/CPS systems
• Compliance with legal, health, and environmental policies
• Conflict resolution between IoT applications
• Secure connectivity and updates in IoT/CPS
• Secure integration of hardware and software systems
• Privacy challenges in IoT/CPS settings
• Privacy preserving data sharing and analysis
• Resiliency against attacks and faults
• Safety in human-in-the-loop systems
• Support for IoT/CPS development - debugging tools, emulators, testbeds
• Usable security and privacy for IoT/CPS platforms
• Smart homes, smart buildings and smart city security and privacy issues

In addition, application domains of interest include, but are not limited to autonomous vehicles and transportation infrastructure; medical CPS and public health; smart buildings, smart grid and smart cities.

The PC will select a best paper award for work that distinguishes itself in moving the security and privacy of IoT/CPS forward through novel attacks or defenses.

Call for Demos

In addition to presentation of accepted papers, SafeThings will include a demo session that is designed to allow researchers to share demonstrations of their systems that include CPS/IoT security and safety as a major design goal. Demos of attacks are also welcome.

---

Submission Instruction

Submitted papers must be in English, unpublished, and must not be currently under review for any other publication. Submissions must follow the official IEEE Conference Proceedings format. Full papers must be at most 6 single-spaced, double column 8.5” x 11” pages excluding references. Demos must be at most 1 single-spaced, double column 8.5” x 11” page, and have "Demo:" in their titles. All figures must fit within these limits. Authors are encouraged to use the IEEE conference proceedings templates. LaTeX submissions should use IEEEtran.cls version 1.8b. Papers that do not meet the size and formatting requirements will not be reviewed. All papers must be in Adobe Portable Document Format (PDF) and submitted through the web submission form via EasyChair (submission link below). The review process is double-blind.

Full Papers: 6 pages excluding references.
Demos: 1 page (with "Demo:" in the title).

Submission Form »

Organization anchor

---

Organization

General Chairs

Qi Alfred Chen (University of California, Irvine)

Yuan Tian (University of Virginia)

Program Committee Chairs

Luis Garcia (University of Southern California Information Sciences Institute)

Earlence Fernandes (University of Wisconsin-Madison)

Web Chair

Junjie Shen (University of California, Irvine)

Technical Program Committee

Mohammad Al Faruque (University of California, Irvine)

Fatima Anwar (UMass Amherst)

Ferdinand Brasser (Technische Universität Darmstadt, Germany)

Berkay Celik (Purdue University)

Rahul Chatterjee (University of Wisconsin-Madison)

Salma Elmalaki (University of California, Irvine)

Sriharsha Etigowni (Purdue University)

Kassem Fawaz (University of Wisconsin-Madison)

Ryan M. Gerdes (Virginia Tech)

Maria Gorlatova (Duke University)

Xiali (Sharon) Hei (University of Louisiana at Lafayette)

Insup Lee (University of Pennsylvania)

Kang Li (Baidu Security)

Zhiqiang Lin (Ohio State University)

Z. Morley Mao (University of Michigan, Ann Arbor)

Sibin Mohan (University of Illinois, Urbana Champaign)

Adwait Nadkarni (William & Mary)

Cristina Nita-Rotaru (Northeastern University)

Jonathan Petit (Qualcomm)

Atul Prakash (University of Michigan, Ann Arbor)

Amir Rahmati (Stony Brook University)

Sara Rampazzi (University of Florida)

Aanjhan Ranganathan (Northeastern University)

Junghwan "John" Rhee (University of Central Oklahoma)

Yasser Shoukry (University of California, Irvine)

Sandeep Shukla (IIT Kanpur, India)

Nils Ole Tippenhauer (CISPA, Germany)

Gene Tsudik (University of California, Irvine)

Jim Weimer (University of Pennsylvania)

André Weimerskirch (Lear Corporation)

Ziming Zhao (University at Buffalo)

Saman Zonouz (Rutgers University)

Steering Committee

Bharathan Balaji (Amazon)

Robin Kravets (University of Illinois, Urbana Champaign)

Mani Srivastava (University of California, Los Angeles)

John A. Stankovic (University of Virginia)

Patrick Tague (Carnegie Mellon University)