Michael Wienczkowski

Michael Wienczkowski

Modern software systems are increasingly developed within rapid continuous integration and deployment (CI/CD) pipelines, where ensuring security prior to release presents significant technical and organizational challenges. Traditional static and dynamic analysis tools provide valuable structural and behavioral insights, yet they often operate in non-adaptive workflows and produce large volumes of warnings requiring manual triage. Feedback-driven fuzzing and search-based testing approaches have demonstrated the power of iterative input refinement guided by execution signals, while large language models (LLMs) have shown promise in automated test generation but frequently lack semantic grounding in program structure. This paper presents a systematic survey of adaptive and AI-augmented security testing research across five domains: (1) structural program analysis for vulnerability detection, (2) DevSecOps and continuous security testing, (3) feedback-driven fuzzing and search-based testing, (4) LLM-based automated test generation, and (5) emerging hybrid systems integrating program analysis with adaptive learning. We analyze fifty-five peer-reviewed studies drawn from a systematic search of four major databases yielding 22,088 raw records. Our analysis reveals a persistent disconnect between structural program representations (ASTs, CFGs, and CPGs) and adaptive testing mechanisms. We characterize this as structural-adaptive fragmentation: a systematic separation that neither paradigm individually addresses. No existing system incorporates human triage signals as feedback for refining structural models. We conclude by identifying five open research challenges and outlining a unified agenda for semantically grounded, feedback-driven, polyglot security testing frameworks.

Michael Wienczkowski, Addisu Desta, Paschal Ugochukwu

Deep learning models are often considered black boxes due to their complex hierarchical transformations. Identifying suitable architectures is crucial for maximizing predictive performance with limited data. Understanding the geometric properties of neural networks involves analyzing their structure, activation functions, and the transformations they perform in high-dimensional space. These properties influence learning, representation, and decision-making. This research explores neural networks through geometric metrics and graph structures, building upon foundational work in arXiv:2007.06559. It addresses the limited understanding of geometric structures governing neural networks, particularly the data manifolds they operate on, which impact classification, optimization, and representation. We identify three key challenges: (1) overcoming linear separability limitations, (2) managing the dimensionality-complexity trade-off, and (3) improving scalability through graph representations. To address these, we propose leveraging non-linear activation functions, optimizing network complexity via pruning and transfer learning, and developing efficient graph-based models. Our findings contribute to a deeper understanding of neural network geometry, supporting the development of more robust, scalable, and interpretable models.