Aggressive Design Reuse for Ubiquitous Zero-Trust Edge Security—From Physical Design to Machine-Learning-Based Hardware Patching

Abstract

This work presents an overview of challenges and solid pathways towards ubiquitous and sustainable hardware security in next-generation silicon chips at the edge of distributed and connected systems (e.g., IoT, AIoT). As first challenge, the increasingly connected nature and the exponential proliferation of edge devices is unabatingly increasing the overall attack surface, making attacks easier and mandating ubiquitous security down to each edge node. At the same time, the necessity to incorporate zero-trust policies in large-scale distributed systems requires a complete set of security primitives for hardware-backed authentication, and a higher degree of physical context awareness (including primitives detecting the onset of physical attacks). Thus, making the inclusion of such security primitives economically sustainable even in low-end devices is a second key challenge. As third challenge, the ever-changing vulnerability landscape and the need for increased chip longevity in distributed systems requires security assurance methods that are sustainable and adaptive across the entire chip lifecycle. In this work, design principles and promising directions to enable ubiquitous and sustainable security capabilities along with physical awareness are discussed. Such achievements require a fundamental rethinking of design methodologies to enable aggressive design and resource reuse (e.g., area, power, design effort), along with low-cost on-chip sensorization and intelligence for physical attack detection. Such rethinking inevitably crosses over the traditional design abstractions, and requires innovation from the physical to the algorithmic level. At the physical and circuit level, design and resource reuse is enabled by immersed-inlogic and in-memory security approaches. At the algorithm level, "hardware patching" is introduced and exemplified to show that run-time intelligence (machine learning) allows security capabilities to adapt and improve over time, as typical of security patching in software. Sensing techniques to detect attacks in situ from non-invasive to invasive are illustrated, while still preserving fully-automated design approaches. Overall, the above design principles are expected to push security capabilities in distributed systems to a new level, ultimately making the edge more intelligent and self-reliant, and security measures more distributed.

A Single-Inverter-Based True Random Number Generator with On-Chip Clock-Tuning-Based Entropy Calibration Circuit

“…It monitors the raw bits generated by entropy source, detects the presence of '0-bias' or '1-bias', then adaptively adds delay time between CLK1 and CLK1B to counter the bias and keep the raw entropy (The Shannon entropy of raw data) greater than 0.8. It comprises two parts, (1). Clock delay generator, (2).…”

“…True random number generator (TRNG) harvests entropy from physical stochastic processes to generate random bits. Low energy and high robustness TRNG is crucial in information security applications of edge devices for generating session keys, nonces, and initialization vectors [1]. In addition to supporting hardware security, TRNG is becoming attractive for non-Von-Neumann computing architecture, such as stochastic computing [2] and neuromorphic computing [3], in which large amounts of random bits are required.…”

Opening of the 2023 Editorial Year—This Coda as Prelude of Next TVLSI Cycle With Sustained Growth

“…1) sustain the Internet of Things in its scaleup toward the trillions of connected devices by removing its economic, logistical and environmental sustainability roadblocks [6]; 2) manage a wider range of transactions with distributed ledgers (e.g., blockchain); 3) enable ubiquitous zero-trust edge security even at the lower end (and cost) of connected devices [7]; 4) make vehicles truly autonomous, connected and collaborative; 5) enhance the human body with new capabilities with augmented senses and powers (e.g., multiscale vision, multimodal sense fusion); 6) make intelligent and assistive robots part of our daily life; 7) enable distributed machine intelligence from edge to cloud while expanding learning at the edge (e.g., wearable, biomedical devices, and smart objects); 8) make information gathering/funneling/retrieval (e.g., from sensors, databases, and web) proactive and context-aware, moving away from "pushing buttons" (i.e., having relevant information being pushed to us as recommendation systems currently do in much narrower applications); 9) sharing goods and services more responsibly, fairly, and efficiently (sharing economy), progressively decoupling socioeconomic progress from intensive use of resources (e.g., through objects augmented with inexpensive smart sensing and tracking); and many others. We have progressed on the above challenges, and they certainly remain highly relevant for the coming years.…”