Related papers: Failure Transparency in Stateful Dataflow Systems …
Recent research shows that colluded malware in different VMs sharing a single physical host may use a resource as a channel to leak critical information. Covert channels employ time or storage characteristics to transmit confidential…
Machine learning systems are increasingly used to support public sector decision-making across a variety of sectors. Given concerns around accountability in these domains, and amidst accusations of intentional or unintentional bias, there…
In recent years, there has been considerable effort to modernize existing and new nuclear power plants with digital instrumentation and control systems. However, there has also been considerable concern both by industry and regulatory…
Observational determinism is a security property that characterizes secure information flow for multithreaded programs. Most of the methods that have been used to verify observational determinism are based on either type systems or…
Traditional machine learning models often prioritize predictive accuracy, often at the expense of model transparency and interpretability. The lack of transparency makes it difficult for organizations to comply with regulatory requirements…
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…
The Task System and Item Architecture (TSIA) is a model for transparent application execution. In many real-world projects, a TSIA provides a simple application with a transparent reliable, distributed, heterogeneous, adaptive, dynamic,…
The integration of Artificial Intelligence (AI) into safety-critical systems introduces a new reliability paradigm: silent failures, where AI produces confident but incorrect outputs that can be dangerous. This paper introduces the Formal…
Increased adoption and deployment of machine learning (ML) models into business, healthcare and other organisational processes, will result in a growing disconnect between the engineers and researchers who developed the models and the…
As artificial intelligence systems increasingly inform high-stakes decisions across sectors, transparency has become foundational to responsible and trustworthy AI implementation. Leveraging our role as a leading institute in advancing AI…
Unintended failures during a computation are painful but frequent during software development. Failures due to external reasons (e.g., missing files, no permissions) can be caught by exception handlers. Programming failures, such as calling…
Serverless computing promises a scalable, reliable, and cost-effective solution for running data-intensive applications and workflows in the heterogeneous and limited-resource environment of the Edge-Cloud Continuum. However, building and…
Field failures, that is, failures caused by faults that escape the testing phase leading to failures in the field, are unavoidable. Improving verification and validation activities before deployment can identify and timely remove many but…
Rising concern for the societal implications of artificial intelligence systems has inspired demands for greater transparency and accountability. However the datasets which empower machine learning are often used, shared and re-used with…
Trusted Execution Environments (TEEs) are gradually adopted by major cloud providers, offering a practical option of \emph{confidential computing} for users who don't fully trust public clouds. TEEs use CPU-enabled hardware features to…
Existing integrity verification approaches for deep models are designed for private verification (i.e., assuming the service provider is honest, with white-box access to model parameters). However, private verification approaches do not…
Recent years have witnessed impressive robotic manipulation systems driven by advances in imitation learning and generative modeling, such as diffusion- and flow-based approaches. As robot policy performance increases, so does the…
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…
Distributed stateful stream processing enables the deployment and execution of large scale continuous computations in the cloud, targeting both low latency and high throughput. One of the most fundamental challenges of this paradigm is…
Along with the wide-adoption of Serverless Computing, more and more applications are developed and deployed on cloud platforms. Major cloud providers present their serverless workflow services to orchestrate serverless functions, making it…