Related papers: Technical Options for Flexible Hardware-Enabled Gu…
Offline Licensing is a mechanism for compute governance that could be used to prevent unregulated training of potentially dangerous frontier AI models. The mechanism works by disabling AI chips unless they have an unused license from a…
Artificial Intelligence (AI) systems are now an integral part of multiple industries. In clinical research, AI supports automated adverse event detection in clinical trials, patient eligibility screening for protocol enrollment, and data…
This paper presents C8s, a confidential computing architecture for Kubernetes that provides cryptographically rooted confidentiality, integrity, and verifiability guarantees for Kubernetes clusters from infrastructure operators. These…
Benchmarks are important measures to evaluate safety and compliance of AI models at scale. However, they typically do not offer verifiable results and lack confidentiality for model IP and benchmark datasets. We propose Attestable Audits,…
AI systems have found a wide range of real-world applications in recent years. The adoption of edge artificial intelligence, embedding AI directly into edge devices, is rapidly growing. Despite the implementation of guardrails and safety…
Reliability in cloud AI infrastructure is crucial for cloud service providers, prompting the widespread use of hardware redundancies. However, these redundancies can inadvertently lead to hidden degradation, so called "gray failure", for AI…
Frontier artificial intelligence (AI) systems present both benefits and risks to society. Safety cases - structured arguments supported by evidence - are one way to help ensure the safe development and deployment of these systems. Yet the…
Although Retrieval-Augmented Generation (RAG) systems have been widely applied, the privacy and security risks they face, such as data leakage and data poisoning, have not been systematically addressed yet. Existing defense strategies…
The increasing prevalence of adversarial attacks on Artificial Intelligence (AI) systems has created a need for innovative security measures. However, the current methods of defending against these attacks often come with a high computing…
Enterprise AI systems, built on large language models, retrieval pipelines and autonomous agents, introduce a class of risks that traditional software quality assurance was never designed to address. These systems are probabilistic,…
Due to the ever-growing demands for electronic chips in different sectors the semiconductor companies have been mandated to offshore their manufacturing processes. This unwanted matter has made security and trustworthiness of their…
Validating FPGA firmware logic used in particle physics is becoming increasingly difficult as the implementation logic scales and becomes more complex with the expansion of FPGA resources. In order to address this issue efficiently, we have…
The implementation, deployment and testing of secure services for Internet of Things devices is nowadays still at an early stage. Several frameworks have recently emerged to help developers realize such services, abstracting the complexity…
Interconnected embedded devices are increasingly used invarious scenarios, including industrial control, building automation, or emergency communication. As these systems commonly process sensitive information or perform safety critical…
Fully Homomorphic Encryption (FHE) is rapidly emerging as a promising foundation for privacy-preserving cloud services, enabling computation directly on encrypted data. As FHE implementations mature and begin moving toward practical…
Prominent AI experts have suggested that companies developing high-risk AI systems should be required to show that such systems are safe before they can be developed or deployed. The goal of this paper is to expand on this idea and explore…
Fully Homomorphic Encryption (FHE) enables the processing of encrypted data without decrypting it. FHE has garnered significant attention over the past decade as it supports secure outsourcing of data processing to remote cloud services.…
We present our Balanced, Integrated and Grounded (BIG) argument for assuring the safety of AI systems. The BIG argument adopts a whole-system approach to constructing a safety case for AI systems of varying capability, autonomy and…
Virtual Trusted Platform modules (TPMs) were proposed as a software-based alternative to the hardware-based TPMs to allow the use of their cryptographic functionalities in scenarios where multiple TPMs are required in a single platform,…
Globalization in the semiconductor industry enables fabless design houses to reduce their costs, save time, and make use of newer technologies. However, the offshoring of Integrated Circuit (IC) fabrication has negative sides, including…