Modern workflows for developing ML pipelines utilize ML artifact management systems (ML AMSs) such as MLflow in addition to traditional version control systems such as Git. ML AMSs collect data, model, metadata and software artifacts used and produced in pipeline development workflows. While ensuring repeatability and reproducibility, the provenance capabilities are still rudimentary, mainly due to incomplete traces, coarse granularity, and limited query capabilities. In this paper, we introduce a comprehensive PROV-compliant provenance model that captures end-to-end provenance traces of ML pipelines, their artifacts, and their relationships based on MLflow and Git activities. Moreover, we present the tool MLflow2PROV for continuously extracting provenance graphs according to our model, enabling querying, analyzing, and processing of the collected provenance information.

Debugging, evaluating, and optimizing stream processing applications is challenging due to continuous streams of input data and typically distributed and parallel execution environments. To address these issues, we present an approach for explorative debugging of stream processing pipelines that allows in-depth investigation of a pipeline's execution behavior and evolution. The time traveling debugger enables traveling back in time within the pipeline's execution history and thoroughly analyzing and retracing each fine-grained step. Any changes made to the pipeline's structure or parameters are captured based on provenance information and can be reviewed, compared, and analyzed with the provenance inspector to understand the impact of each alteration on the quality of the pipeline.

The explorative and iterative nature of developing and operating machine learning (ML) applications leads to a variety of ML artifacts, such as datasets, models, hyperparameters, metrics, software, and configurations. To enable comparability, traceability, and reproducibility of ML artifacts across the ML lifecycle steps and iterations, platforms, frameworks, and tools have been developed to support their collection, storage, and management. Selecting the best-suited ML artifact management systems (AMSs) for a particular use case is often challenging and time-consuming due to the plethora of AMSs, their different focus, and imprecise specifications of features and properties. Based on assessment criteria and their application to a representative selection of more than 60 AMSs, this paper introduces an interactive web tool that enables the convenient and time-efficient exploration and comparison of ML AMSs.

This paper tackles the problem of memory-safe implementation of the AppSPEAR framework for application-level security policy enforcement. We contribute with a feasibility study that demonstrates the performance overhead of applying Rust's memory safety features on top of SGX trusted execution technology.

Attribute-based access control (ABAC) has made its way into the mainstream of engineering secure IT systems. At the same time, ABAC models are still lagging behind well-understood, yet more basic access control models in terms of dynamic analyzability. This has led to a plethora of methods, languages, and tools for designing and integrating ABAC policies, but only few to formally reason about them in the process. We present DABAC, a modeling scheme to pick up that missing piece and put it right into its place in the security engineering workflow. Based on an automaton calculus, we demonstrate how DABAC can be leveraged as a holistic formal basis for engineering ABAC models, analyzing their dynamic properties, and providing a functional specification for their implementation. This sets the stage for comprehensive tool support in building future ABAC systems.

While there have been approaches for integrating security policies into operating systems (OSs) for more than two decades, applications often use objects of higher abstraction requiring individual security policies with application-specific semantics. Due to insufficient OS support, current approaches for enforcing application-level policies typically lead to large and complex trusted computing bases rendering tamperproofness and correctness difficult to achieve. To mitigate this problem, we propose the application-level policy enforcement architecture APPSPEAR and a C++ framework for its implementation. The configurable framework enables developers to balance enforcement rigor and costs imposed by different implementation alternatives and to easily tailor an APPSPEAR implementation to individual application requirements. We argue that hardware-based trusted execution environments offer an optimal balance between effectiveness and efficiency of policy protection and enforcement. This claim is substantiated by a practical evaluation based on a medical record system.