February 2021

Our NSF Cyber Physical Systems (CPS) project proposal is awarded and starts. The project for 3 years is joint between Purdue CS (Aniket Kate), ECE (Saurabh), ABE (Somali Chaterji) and Duke CS (Mike Reiter). It is titled “COPIA: Secure Distributed Protocols for Energy-Constrained Cyber Physical Systems” and is funded for a little over $1M.

Purdue University: Computer Science Professional Masters Degree: Faculty
Purdue University - Department of Computer Science - Saurabh Bagchi
Bringing the cloud back down to earth | by Purdue College of Engineering |  Purdue Engineering Review | Medium
Michael Kendrick Reiter | Duke Pratt School of Engineering

Cyber-physical systems (CPS) have now started to play an increasingly important role in autonomous sensing, analysis, and tasking in a variety of agricultural settings ranging from sustainable farming to livestock monitoring. Many of these settings demand real-time analytics, at varying timescales, and the CPS devices have to coordinate among themselves over a variety of wireless networks. As various actors in these settings—from farmers to big agro companies—have much to gain from manipulating the results of these distributed systems, it is important to make these systems fault-tolerant and secure. This project, COPIA, seeks to provide the fundamental secure distributed computing primitives tailored for real-time agro-analytics in the face of malicious faults and network failures.

A high-level schematic of multi-tier CPS scenarios in COPIA. For the soil monitoring scenario on the left, we propose that Tier 3 nodes on the ground communicate with each other in real-time (blue lines) to perform consensus, and then offer aggregate information back to the infrequent drones (Tier 2 nodes). For the livestock monitoring scenario, Tier 3 nodes are attached to the animals and so are very light-weight. Tier 3 nodes are not expected to communicate with other; however, instead they offer data to static communication gateways (Tier 2S nodes) and/or mobile drones (Tier 2M nodes). Tier 2 nodes communicate with each other over long-range communication (Purple) channels. In COPIA, the Tier 2M nodes perform dynamic (approximate) consensus, and we will also explore two-tier consensus across the Tier 2S and Tier 2M nodes. Adversaries can compromise nodes and links.

Despite more than four decades of work on secure distributed computing, this CPS domain introduces new requirements that COPIA will address through fundamental innovations. First, COPIA will incorporate a principled framework for comparing energy costs of protocols and deriving optimal choices of cryptographic primitives to optimize energy use. This framework will permit leveraging CPS-specific opportunities, e.g., the difficulty for an adversary to equivocate (or offer two conflicting statements to two different neighbors) due to the omnidirectional nature of wireless links. Second, COPIA will achieve consensus in dynamic networks, i.e., where CPS nodes are mobile (e.g., drones). The technical challenge here is that the communication graph of nodes dynamically changes; most existing work assumes graph connectivity is unchanging throughout the execution of the protocol. Third, COPIA will address privacy in these distributed computing protocols, as the farmers are increasingly worried about companies extracting trade secrets from sensor data. This thrust involves hardening distributed computing protocols so that a limited number of node compromises does not divulge secrets.