Selected work

Representative Papers

Financing Artificial Intelligence Infrastructure: Mapping AI Infrastructure Investment and Compute Governance Across Africa

Jun 24, 2026

Current AI governance frameworks disproportionately emphasize the geographic accessibility of computational power while neglecting the underlying dynamics of capital flows, ownership structures, and control mechanisms, thereby falling short of achieving genuine compute equity. This study systematically examines 46 AI infrastructure projects across Africa between 2019 and 2025, representing a total investment of $12.7 billion, integrating systematic literature review, publicly available data, and a value chain analysis framework. It reveals that 73% of funding is concentrated in capital and physical infrastructure, with compute control heavily centralized among a few global technology giants, and investments markedly clustered in South Africa, Kenya, Nigeria, and Egypt. Introducing the concept of “asymmetric interdependence,” this work advocates for incorporating capital, ownership, and control dimensions into compute governance to transcend the prevailing paradigm centered solely on technological access.

0 citationsRead paper

Exploring Statistical Change Point Detection Techniques for Performance Anomaly Detection at Mozilla

Jun 16, 2026

This work addresses the high false positive rate (12.5%) and false negative rate (6.8%) of Mozilla’s existing T-test–based performance anomaly detection system, which hampers continuous integration efficiency. The authors introduce the first benchmark dataset comprising 174 engineer-annotated performance time series and conduct a systematic evaluation of 25 change-point detection algorithms combined with 15 ensemble strategies. They propose an ensemble voting mechanism that integrates offline, online, and hybrid methods to effectively mitigate the precision–recall trade-off. Experimental results and engineer feedback demonstrate that the proposed approach improves the F1-score by 11% over the original system and has been successfully integrated into Mozilla’s performance engineering infrastructure.

0 citationsRead paper

Reimagining Open Source and Openness in AI: Co-Creating Responsible Technological Futures

Jun 05, 2026

This study addresses the empirical gap in multi-stakeholder deliberation within current AI governance frameworks, which hinders the realization of “responsible openness” that balances innovation, accountability, and public interest. Through participatory workshops involving diverse sectors and integrating futures thinking with co-design methodologies, this project systematically documents stakeholders’ collective aspirations regarding AI openness for the first time. The research identifies four core tensions across purpose, scope, and operational dimensions, demonstrating that responsible openness is fundamentally a value-driven sociotechnical negotiation process. Key outputs include a shared vision of collaborative intent, actionable pathways, and a research roadmap, offering both empirical grounding and methodological innovation to advance AI governance beyond dominant corporate narratives.

0 citationsRead paper

Polars inside Intel SGX2 Enclaves: An Empirical Study of Confidential Analytical Query Processing

May 20, 2026

This study addresses the lack of systematic performance evaluation of Arrow-native analytics engines within Intel SGX2 trusted execution environments, particularly under large-scale data and realistic cloud storage conditions. For the first time, we execute Polars—an Arrow-native DataFrame library—inside an SGX2 enclave using Gramine, conducting end-to-end measurements of query computation and data loading overheads based on the TPC-H SF30 benchmark and Azure Blob Storage. We further compare lazy and eager execution modes. Our experiments reveal that overall overhead remains stable between 1.49× and 1.56×; computation overhead decreases with larger datasets while data loading overhead increases significantly. Lazy execution outperforms eager execution by more than 2.25× and effectively avoids out-of-memory errors under high memory pressure, highlighting the critical impact of API design choices on both performance and resource utilization.

0 citationsRead paper

Risk-Aware Batch Testing for Performance Regression Detection

Mar 31, 2026

This study addresses the high cost of full-scale performance regression testing in large-scale continuous integration (CI), where existing approaches struggle to balance submission heterogeneity and resource efficiency. The work proposes the first framework integrating commit-level regression risk prediction with dynamic batching, introducing novel risk-aware scheduling strategies such as Risk-Aged Priority Batching (RAPB). Leveraging real-world Mozilla Firefox datasets, the authors fine-tune ModernBERT, CodeBERT, and LLaMA-3.1 models to predict regression risk and validate their approach through CI simulation. The optimal configuration, RAPB-la, reduces test execution volume by 32.4%, shortens average feedback time by 3.8%, decreases maximum localization latency by 26.2%, and yields an estimated annual infrastructure cost saving of approximately $491,000.

0 citationsRead paper

Recent publications

Latest Papers

Financing Artificial Intelligence Infrastructure: Mapping AI Infrastructure Investment and Compute Governance Across Africa

Jun 24, 2026

Current AI governance frameworks disproportionately emphasize the geographic accessibility of computational power while neglecting the underlying dynamics of capital flows, ownership structures, and control mechanisms, thereby falling short of achieving genuine compute equity. This study systematically examines 46 AI infrastructure projects across Africa between 2019 and 2025, representing a total investment of $12.7 billion, integrating systematic literature review, publicly available data, and a value chain analysis framework. It reveals that 73% of funding is concentrated in capital and physical infrastructure, with compute control heavily centralized among a few global technology giants, and investments markedly clustered in South Africa, Kenya, Nigeria, and Egypt. Introducing the concept of “asymmetric interdependence,” this work advocates for incorporating capital, ownership, and control dimensions into compute governance to transcend the prevailing paradigm centered solely on technological access.

0 citationsRead paper

Exploring Statistical Change Point Detection Techniques for Performance Anomaly Detection at Mozilla

Jun 16, 2026

This work addresses the high false positive rate (12.5%) and false negative rate (6.8%) of Mozilla’s existing T-test–based performance anomaly detection system, which hampers continuous integration efficiency. The authors introduce the first benchmark dataset comprising 174 engineer-annotated performance time series and conduct a systematic evaluation of 25 change-point detection algorithms combined with 15 ensemble strategies. They propose an ensemble voting mechanism that integrates offline, online, and hybrid methods to effectively mitigate the precision–recall trade-off. Experimental results and engineer feedback demonstrate that the proposed approach improves the F1-score by 11% over the original system and has been successfully integrated into Mozilla’s performance engineering infrastructure.

0 citationsRead paper

Reimagining Open Source and Openness in AI: Co-Creating Responsible Technological Futures

Jun 05, 2026

This study addresses the empirical gap in multi-stakeholder deliberation within current AI governance frameworks, which hinders the realization of “responsible openness” that balances innovation, accountability, and public interest. Through participatory workshops involving diverse sectors and integrating futures thinking with co-design methodologies, this project systematically documents stakeholders’ collective aspirations regarding AI openness for the first time. The research identifies four core tensions across purpose, scope, and operational dimensions, demonstrating that responsible openness is fundamentally a value-driven sociotechnical negotiation process. Key outputs include a shared vision of collaborative intent, actionable pathways, and a research roadmap, offering both empirical grounding and methodological innovation to advance AI governance beyond dominant corporate narratives.

0 citationsRead paper

Polars inside Intel SGX2 Enclaves: An Empirical Study of Confidential Analytical Query Processing

May 20, 2026

This study addresses the lack of systematic performance evaluation of Arrow-native analytics engines within Intel SGX2 trusted execution environments, particularly under large-scale data and realistic cloud storage conditions. For the first time, we execute Polars—an Arrow-native DataFrame library—inside an SGX2 enclave using Gramine, conducting end-to-end measurements of query computation and data loading overheads based on the TPC-H SF30 benchmark and Azure Blob Storage. We further compare lazy and eager execution modes. Our experiments reveal that overall overhead remains stable between 1.49× and 1.56×; computation overhead decreases with larger datasets while data loading overhead increases significantly. Lazy execution outperforms eager execution by more than 2.25× and effectively avoids out-of-memory errors under high memory pressure, highlighting the critical impact of API design choices on both performance and resource utilization.

0 citationsRead paper

Risk-Aware Batch Testing for Performance Regression Detection

Mar 31, 2026

This study addresses the high cost of full-scale performance regression testing in large-scale continuous integration (CI), where existing approaches struggle to balance submission heterogeneity and resource efficiency. The work proposes the first framework integrating commit-level regression risk prediction with dynamic batching, introducing novel risk-aware scheduling strategies such as Risk-Aged Priority Batching (RAPB). Leveraging real-world Mozilla Firefox datasets, the authors fine-tune ModernBERT, CodeBERT, and LLaMA-3.1 models to predict regression risk and validate their approach through CI simulation. The optimal configuration, RAPB-la, reduces test execution volume by 32.4%, shortens average feedback time by 3.8%, decreases maximum localization latency by 26.2%, and yields an estimated annual infrastructure cost saving of approximately $491,000.

0 citationsRead paper