Related papers: Flexible Hardware-Enabled Guarantees for AI Comput…
Vertical federated learning (VFL) leverages various privacy-preserving algorithms, e.g., homomorphic encryption or secret sharing based SecureBoost, to ensure data privacy. However, these algorithms all require a semi-honest secure…
We propose that future AI transparency and accountability regulations are based on an open global standard for exchanging information about AI systems, which allows co-existence of potentially conflicting local regulations. Then, we discuss…
Evaluating the safety of AI Systems is a pressing concern for organizations deploying them. In addition to the societal damage done by the lack of fairness of those systems, deployers are concerned about the legal repercussions and the…
Artificial Intelligence Generated Content (AIGC) is one of the latest achievements in AI development. The content generated by related applications, such as text, images and audio, has sparked a heated discussion. Various derived AIGC…
This paper presents composable attestation as a generalized cryptographic framework for Continuous and Incremental Trust in Distributed Systems,such as Artificial Intelligence (AI) computation, and Open Source Software (OSS) supply chain…
Financial systems have a growing reliance on computer-based and distributed systems, making FinTech systems vulnerable to advanced and quickly emerging cyber-criminal threats. Traditional security systems and fixed machine learning systems…
This research paper explores the privacy and security threats posed to an Agentic AI system with direct access to database systems. Such access introduces significant risks, including unauthorized retrieval of sensitive information,…
Because FPGAs outperform traditional processing cores like CPUs and GPUs in terms of performance per watt and flexibility, they are being used more and more in cloud and data center applications. There are growing worries about the security…
There is still a significant gap between expectations and the successful adoption of AI to innovate and improve businesses. Due to the emergence of deep learning, AI adoption is more complex as it often incorporates big data and the…
Integrating Field Programmable Gate Arrays (FPGAs) with cloud computing instances is a rapidly emerging trend on commercial cloud computing platforms such as Amazon Web Services (AWS), Huawei cloud, and Alibaba cloud. Cloud FPGAs allow…
In the factory of the future traditional and formerly isolated Operational Technology (OT) hardware will become connected with all kinds of networks. This leads to more complex security challenges during design, deployment and use of…
The integration of Generative Artificial Intelligence (GenAI) in healthcare is impeded by significant security challenges unaddressed by traditional frameworks, precisely the data-in-use gap where sensitive patient data and proprietary AI…
We outline the principles of classical assurance for computer-based systems that pose significant risks. We then consider application of these principles to systems that employ Artificial Intelligence (AI) and Machine Learning (ML). A key…
Trusted execution environments in several existing and upcoming CPUs demonstrate the success of confidential computing, with the caveat that tenants cannot securely use accelerators such as GPUs and FPGAs. In this paper, we reconsider the…
The rapid integration of AI algorithms in safety-critical applications such as autonomous driving and healthcare is raising significant concerns about the ability to meet stringent safety standards. Traditional tools for formal safety…
Homomorphic encryption enables computations on encrypted data without accessing private keys, enhancing security in cloud environments. Without this technology, updates need to be performed on-premises or require transmitting private keys…
Concerns about the societal impact of AI-based services and systems has encouraged governments and other organisations around the world to propose AI policy frameworks to address fairness, accountability, transparency and related topics. To…
Autonomous AI agents powered by large language models are being deployed in production with capabilities including shell execution, file system access, database queries, and multi-party communication. Recent red teaming research…
Accuracy is an important concern for suppliers of artificial intelligence (AI) services, but considerations beyond accuracy, such as safety (which includes fairness and explainability), security, and provenance, are also critical elements…
This document presents a vision for a novel AI infrastructure design that has been initially validated through inference simulations on state-of-the-art large language models. Advancements in deep learning and specialized hardware have…