Related papers: Technical Options for Flexible Hardware-Enabled Gu…
The United States Department of Defense (DOD) looks to accelerate the development and deployment of AI capabilities across a wide spectrum of defense applications to maintain strategic advantages. However, many common features of AI…
As artificial intelligence systems grow more capable and autonomous, frontier AI development poses potential systemic risks that could affect society at a massive scale. Current practices at many AI labs developing these systems lack…
Modern Integrated Circuits (ICs) are becoming increasingly complex, and so is their development process. Hardware design verification entails a methodical and disciplined approach to the planning, development, execution, and sign-off of…
The increasing integration of Artificial Intelligence across multiple industry sectors necessitates robust mechanisms for ensuring transparency, trust, and auditability of its development and deployment. This topic is particularly important…
Edge deployment of transformer-based models increasingly relies on ASIC accelerators due to their high performance and energy efficiency, achieved through optimized dataflows, specialized architectures, low-bitwidth computation, and…
As hardware systems grow in complexity, security verification must keep up with them. Recently, artificial intelligence (AI) and large language models (LLMs) have started to play an important role in automating several stages of the…
Frontier AI developers operate at the intersection of rapid technical progress, extreme risk exposure, and growing regulatory scrutiny. While a range of external evaluations and safety frameworks have emerged, comparatively little attention…
To address the risks of increasingly capable AI systems, we introduce a hardware-level off-switch that embeds thousands of independent "security blocks" in each AI accelerator. This massively redundant architecture is designed to prevent…
Today, there is a trend to incorporate more intelligence (e.g., vision capabilities) into a wide range of devices, which makes high performance a necessity for computing systems. Furthermore, for embedded systems, low power consumption…
The rapid adaptation of data driven AI models, such as deep learning inference, training, Vision Transformers (ViTs), and other HPC applications, drives a strong need for runtime precision configurable different non linear activation…
Hardware-secured remote attestation is essential to establishing trust in the integrity of confidential virtual machines (cVMs), but is difficult to use in practice because verifying attestation evidence requires the use of…
Safety cases - clear, assessable arguments for the safety of a system in a given context - are a widely-used technique across various industries for showing a decision-maker (e.g. boards, customers, third parties) that a system is safe. In…
As AI rapidly advances, the security risks posed by AI are becoming increasingly severe, especially in critical scenarios, including those posing existential risks. If AI becomes uncontrollable, manipulated, or actively evades safety…
International agreements about AI development may be required to reduce catastrophic risks from advanced AI systems. However, agreements about such a high-stakes technology must be backed by verification mechanisms--processes or tools that…
The increasing adoption of System-on-Chip Field-Programmable Gate Arrays (SoC FPGAs) in AI-enabled satellite systems, valued for their reconfigurability and in-orbit update capabilities, introduces significant security challenges.…
Fully homomorphic encryption (FHE) has experienced significant development and continuous breakthroughs in theory, enabling its widespread application in various fields, like outsourcing computation and secure multi-party computing, in…
With the rapid development and integration of artificial intelligence (AI) methods in next-generation networks (NextG), AI algorithms have provided significant advantages for NextG in terms of frequency spectrum usage, bandwidth, latency,…
Process attestation systems verify that a continuous physical process, such as human authorship, actually occurred, rather than merely checking system state. These systems face a fundamental dependability challenge: the evidence collection…
SAFE is a clean-slate design for a highly secure computer system, with pervasive mechanisms for tracking and limiting information flows. At the lowest level, the SAFE hardware supports fine-grained programmable tags, with efficient and…
Fully homomorphic encryption (FHE) is in the spotlight as a definitive solution for privacy, but the high computational overhead of FHE poses a challenge to its practical adoption. Although prior studies have attempted to design ASIC…