Related papers: Automated Verification of Accountability in Securi…
We define a problem of certifying computation integrity performed by some remote party we do not necessarily trust. We present a multi-party interactive protocol called SafeComp that solves this problem under specified constraints.…
Widespread adoption of autonomous cars will require greater confidence in their safety than is currently possible. Certified control is a new safety architecture whose goal is two-fold: to achieve a very high level of safety, and to provide…
Safety architectures play a crucial role in the safety assurance of automated driving vehicles (ADVs). They can be used as safety envelopes of black-box ADV controllers, and for graceful degradation from one ODD to another. Building on our…
Verification is the process of checking whether a product has been implemented according to its prescribed specifications. We study the case of a designer (the developer) that needs to verify its design by a third party (the verifier), by…
We present a composably secure protocol allowing $n$ parties to test an entanglement generation resource controlled by a possibly dishonest party. The test consists only in local quantum operations and authenticated classical communication…
AI deployment in sensitive domains such as health care, credit, employment, and criminal justice is often treated as unsafe to authorize until model internals can be explained. This often leads to an excessive reliance on mechanistic…
This article describes a fully automated, credible autocoding chain for control systems. The framework generates code, along with guarantees of high level functional properties which can be independently verified. It relies on domain…
Cryptographic protocols aim at securing communications over insecure networks such as the Internet, where dishonest users may listen to communications and interfere with them. A secure communication has a different meaning depending on the…
In this briefing report, we introduce a new concept (war algorithms) that elevates algorithmically-derived choices and decisions to a, and perhaps the, central concern regarding technical autonomy in war. We thereby aim to shed light on and…
Frontier AI systems require governance mechanisms that can verify internal alignment, not just behavioral compliance. Private governance mechanisms audits, certification, insurance, and procurement are emerging to complement public…
This vision paper presents initial research on assessing the robustness and reliability of AI-enabled systems, and key factors in ensuring their safety and effectiveness in practical applications, including a focus on accountability. By…
When studying safety properties of (formal) protocol models, it is customary to view the scheduler as an adversary: an entity trying to falsify the safety property. We show that in the context of security protocols, and in particular of…
As the IoT becomes increasingly ubiquitous, concerns are being raised about how IoT systems are being built and deployed. Connected devices will generate vast quantities of data, which drive algorithmic systems and result in real-world…
This article offers several contributions to the interdisciplinary project of responsible research and innovation in data science and AI. First, it provides a critical analysis of current efforts to establish practical mechanisms for…
Designing provably safe control is a core problem in trustworthy autonomy. However, most prior work in this regard assumes either that the system dynamics are known or deterministic, or that the state and action space are finite,…
Motivated by proof-of-stake (PoS) blockchains such as Ethereum, two key desiderata have recently been studied for Byzantine-fault tolerant (BFT) state-machine replication (SMR) consensus protocols: Finality means that the protocol retains…
The deployment of autonomous agents in environments involving human interaction has increasingly raised security concerns. Consequently, understanding the circumstances behind an event becomes critical, requiring the development of…
Auditability is defined as the capacity of AI systems to be independently assessed for compliance with ethical, legal, and technical standards throughout their lifecycle. The chapter explores how auditability is being formalized through…
Transparency protocols are protocols whose actions can be publicly monitored by observers (such observers may include regulators, rights advocacy groups, or the general public). The observed actions are typically usages of private keys such…
Modern cloud-based AI training relies on extensive telemetry and logs to ensure accountability. While these audit trails enable retrospective inspection, they struggle to address the inherent non-determinism of deep learning. Stochastic…