Related papers: Provenance Threat Modeling
While Machine Learning (ML) technologies are widely adopted in many mission critical fields to support intelligent decision-making, concerns remain about system resilience against ML-specific security attacks and privacy breaches as well as…
Provenance has been thought of a mechanism to verify a workflow and to provide workflow reproducibility. This provenance of scientific workflows has been effectively carried out in Grid based scientific workflow systems. However, recent…
Modern cyber attackers use advanced zero-day exploits, highly targeted spear phishing, and other social engineering techniques to gain access and also use evasion techniques to maintain a prolonged presence within the victim network while…
We outline the approach being developed in the neuGRID project to use provenance management techniques for the purposes of capturing and preserving the provenance data that emerges in the specification and execution of workflows in…
We outline the approach being developed in the neuGRID project to use provenance management techniques for the purposes of capturing and preserving the provenance data that emerges in the specification and execution of workflows in…
In the context of Open Science, provenance has become a decisive piece of information to provide along with astronomical data. Provenance is explicitly cited in the FAIR principles, that aims to make research data Findable, Accessible,…
As users become confronted with a deluge of provenance data, dedicated techniques are required to make sense of this kind of information. We present Aggregation by Provenance Types, a provenance graph analysis that is capable of generating…
Provenance encodes information that connects datasets, their generation workflows, and associated metadata (e.g., who or when executed a query). As such, it is instrumental for a wide range of critical governance applications (e.g.,…
Machine learning models are vulnerable to simple model stealing attacks if the adversary can obtain output labels for chosen inputs. To protect against these attacks, it has been proposed to limit the information provided to the adversary…
An interesting research problem in our age of Big Data is that of determining provenance. Granular evaluation of provenance of physical goods--e.g. tracking ingredients of a pharmaceutical or demonstrating authenticity of luxury goods--has…
This paper presents an approach to formalizing and enforcing a class of use privacy properties in data-driven systems. In contrast to prior work, we focus on use restrictions on proxies (i.e. strong predictors) of protected information…
As more and more applications and services depend on data collected and provided by Internet of Things (IoT) devices, it is of importance that such data can be trusted. Data provenance solutions together with blockchain technology are one…
Scientific workflow systems increasingly store provenance information about the module executions used to produce a data item, as well as the parameter settings and intermediate data items passed between module executions. However,…
Robot behavior is often validated through simulation-based testing, yet the replicability of such campaigns depends critically on transparent documentation of how tests are configured, executed, and post-processed. We argue that data…
Production machine learning systems are consistently under attack by adversarial actors. Various deep learning models must be capable of accurately detecting fake or adversarial input while maintaining speed. In this work, we propose one…
Transfer learning, also referred as knowledge transfer, aims at reusing knowledge from a source dataset to a similar target one. While many empirical studies illustrate the benefits of transfer learning, few theoretical results are…
Dependability is an umbrella concept that subsumes many key properties about a system, including reliability, maintainability, safety, availability, confidentiality, and integrity. Various dependability modeling techniques have been…
High availability of data is responsible for the current trends in Artificial Intelligence (AI) and Machine Learning (ML). However, high-grade datasets are reluctantly shared between actors because of lacking trust and fear of losing…
New capabilities in foundation models are owed in large part to massive, widely-sourced, and under-documented training data collections. Existing practices in data collection have led to challenges in tracing authenticity, verifying…
Provenance is derivative journal information about the origin and activities of system data and processes. For a highly dynamic system like the cloud, provenance can be accurately detected and securely used in cloud digital forensic…