@article{scaramuzza_accountability_2025,

title = {Accountability of Robust and Reliable AI-Enabled Systems: A Preliminary Study and Roadmap},

author = {F. Scaramuzza and D. A. Tamburri and W. J. van den Heuvel},

url = {http://arxiv.org/abs/2506.16831},

doi = {10.48550/arXiv.2506.16831},

year  = {2025},

date = {2025-06-01},

urldate = {2025-06-01},

abstract = {This vision paper presents initial research on assessing the robustness and reliability of AI-enabled systems, and key factors in ensuring their safety and effectiveness in practical applications, including a focus on accountability. By exploring evolving definitions of these concepts and reviewing current literature, the study highlights major challenges and approaches in the field. A case study is used to illustrate real-world applications, emphasizing the need for innovative testing solutions. The incorporation of accountability is crucial for building trust and ensuring responsible AI development. The paper outlines potential future research directions and identifies existing gaps, positioning robustness, reliability, and accountability as vital areas for the development of trustworthy AI systems of the future.},

note = {arXiv:2506.16831 [cs]},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{owotogbe_chaos_2025,

title = {Chaos Engineering: A Multi-Vocal Literature Review},

author = {J. Owotogbe and I. Kumara and W. J. van den Heuvel and D. A. Tamburri},

url = {http://arxiv.org/abs/2412.01416},

doi = {10.48550/arXiv.2412.01416},

year  = {2025},

date = {2025-06-01},

urldate = {2025-06-01},

abstract = {Organizations, particularly medium and large enterprises, typically rely heavily on complex, distributed systems to deliver critical services and products. However, the growing complexity of these systems poses challenges in ensuring service availability, performance, and reliability. Traditional resilience testing methods often fail to capture the intricate interactions and failure modes of modern systems. Chaos Engineering addresses these challenges by proactively testing how systems in production behave under turbulent conditions, allowing developers to uncover and resolve potential issues before they escalate into outages. Though chaos engineering has received growing attention from researchers and practitioners alike, we observed a lack of reviews that synthesize insights from both academic and grey literature. Hence, we conducted a Multivocal Literature Review (MLR) on chaos engineering to address this research gap by systematically analyzing 96 academic and grey literature sources published between January 2016 and April 2024. We first used the chosen sources to derive a unified definition of chaos engineering and to identify key functionalities, components, and adoption drivers. We also developed a taxonomy for chaos engineering platforms and compared the relevant tools using it. Finally, we analyzed the current state of chaos engineering research and identified several open research issues.},

note = {arXiv:2412.01416 [cs]},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{kaplan_systematic_2025,

title = {Systematic Testing of Security-Related Vulnerabilities in LLM-Based Applications},

author = {H. Kaplan},

url = {https://www.researchgate.net/publication/392750563_Systematic_Testing_of_Security-Related_Vulnerabilities_in_LLM-Based_Applications},

doi = {10.1109/CAIN66642.2025.00043},

year  = {2025},

date = {2025-06-01},

urldate = {2025-06-01},

journal = {ResearchGate},

abstract = {Download Citation textbar On Apr 27, 2025, Hasan Kaplan published Systematic Testing of Security-Related Vulnerabilities in LLM-Based Applications textbar Find, read and cite all the research you need on ResearchGate},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{scaramuzza_engineering_2025,

title = {Engineering Trustworthy Machine-Learning Operations with Zero-Knowledge Proofs},

author = {F. Scaramuzza and G. Quattrocchi and D. A. Tamburri},

url = {http://arxiv.org/abs/2505.20136},

doi = {10.48550/arXiv.2505.20136},

year  = {2025},

date = {2025-05-01},

urldate = {2025-05-01},

abstract = {As Artificial Intelligence (AI) systems, particularly those based on machine learning (ML), become integral to high-stakes applications, their probabilistic and opaque nature poses significant challenges to traditional verification and validation methods. These challenges are exacerbated in regulated sectors requiring tamper-proof, auditable evidence, as highlighted by apposite legal frameworks, e.g., the EU AI Act. Conversely, Zero-Knowledge Proofs (ZKPs) offer a cryptographic solution that enables provers to demonstrate, through verified computations, adherence to set requirements without revealing sensitive model details or data. Through a systematic survey of ZKP protocols, we identify five key properties (non-interactivity, transparent setup, standard representations, succinctness, and post-quantum security) critical for their application in AI validation and verification pipelines. Subsequently, we perform a follow-up systematic survey analyzing ZKP-enhanced ML applications across an adaptation of the Team Data Science Process (TDSP) model (Data & Preprocessing, Training & Offline Metrics, Inference, and Online Metrics), detailing verification objectives, ML models, and adopted protocols. Our findings indicate that current research on ZKP-Enhanced ML primarily focuses on inference verification, while the data preprocessing and training stages remain underexplored. Most notably, our analysis identifies a significant convergence within the research domain toward the development of a unified Zero-Knowledge Machine Learning Operations (ZKMLOps) framework. This emerging framework leverages ZKPs to provide robust cryptographic guarantees of correctness, integrity, and privacy, thereby promoting enhanced accountability, transparency, and compliance with Trustworthy AI principles.},

note = {arXiv:2505.20136 [cs]},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{owotogbe_assessing_2025,

title = {Assessing and Enhancing the Robustness of LLM-based Multi-Agent Systems Through Chaos Engineering},

author = {J. Owotogbe},

url = {http://arxiv.org/abs/2505.03096},

doi = {10.48550/arXiv.2505.03096},

year  = {2025},

date = {2025-05-01},

urldate = {2025-05-01},

abstract = {This study explores the application of chaos engineering to enhance the robustness of Large Language Model-Based Multi-Agent Systems (LLM-MAS) in production-like environments under real-world conditions. LLM-MAS can potentially improve a wide range of tasks, from answering questions and generating content to automating customer support and improving decision-making processes. However, LLM-MAS in production or preproduction environments can be vulnerable to emergent errors or disruptions, such as hallucinations, agent failures, and agent communication failures. This study proposes a chaos engineering framework to proactively identify such vulnerabilities in LLM-MAS, assess and build resilience against them, and ensure reliable performance in critical applications.},

note = {arXiv:2505.03096 [cs]},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{moharil_recursive_2025,

title = {Recursive Self-Similarity in Deep Weight Spaces of Neural Architectures: A Fractal and Coarse Geometry Perspective},

author = {A. Moharil and I. Kumara and D. A. Tamburri and M. Mohammadi and W. J. van den Heuvel},

url = {http://arxiv.org/abs/2503.14298},

doi = {10.48550/arXiv.2503.14298},

year  = {2025},

date = {2025-03-01},

urldate = {2025-03-01},

abstract = {This paper conceptualizes the Deep Weight Spaces (DWS) of neural architectures as hierarchical, fractal-like, coarse geometric structures observable at discrete integer scales through recursive dilation. We introduce a coarse group action termed the fractal transformation, $T_r_k $, acting under the symmetry group $G = (textbackslashmathbbZ, +) $, to analyze neural parameter matrices or tensors, by segmenting the underlying discrete grid $textbackslashOmega$ into $N(r_k)$ fractals across varying observation scales $ r_k $. This perspective adopts a box count technique, commonly used to assess the hierarchical and scale-related geometry of physical structures, which has been extensively formalized under the topic of fractal geometry. We assess the structural complexity of neural layers by estimating the Hausdorff-Besicovitch dimension of their layers and evaluating a degree of self-similarity. The fractal transformation features key algebraic properties such as linearity, identity, and asymptotic invertibility, which is a signature of coarse structures. We show that the coarse group action exhibits a set of symmetries such as Discrete Scale Invariance (DSI) under recursive dilation, strong invariance followed by weak equivariance to permutations, alongside respecting the scaling equivariance of activation functions, defined by the intertwiner group relations. Our framework targets large-scale structural properties of DWS, deliberately overlooking minor inconsistencies to focus on significant geometric characteristics of neural networks. Experiments on CIFAR-10 using ResNet-18, VGG-16, and a custom CNN validate our approach, demonstrating effective fractal segmentation and structural analysis.},

note = {arXiv:2503.14298 [cs]},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{moharil_towards_2024,

title = {Towards efficient AutoML: a pipeline synthesis approach leveraging pre-trained transformers for multimodal data},

author = {A. Moharil and J. Vanschoren and P. Singh and D. Tamburri},

url = {https://doi.org/10.1007/s10994-024-06568-1},

doi = {10.1007/s10994-024-06568-1},

issn = {1573-0565},

year  = {2024},

date = {2024-09-01},

urldate = {2024-09-01},

journal = {Machine Learning},

volume = {113},

number = {9},

pages = {7011–7053},

abstract = {This paper introduces an Automated Machine Learning (AutoML) framework specifically designed to efficiently synthesize end-to-end multimodal machine learning pipelines. Traditional reliance on the computationally demanding Neural Architecture Search is minimized through the strategic integration of pre-trained transformer models. This innovative approach enables the effective unification of diverse data modalities into high-dimensional embeddings, streamlining the pipeline development process. We leverage an advanced Bayesian Optimization strategy, informed by meta-learning, to facilitate the warm-starting of the pipeline synthesis, thereby enhancing computational efficiency. Our methodology demonstrates its potential to create advanced and custom multimodal pipelines within limited computational resources. Extensive testing across 23 varied multimodal datasets indicates the promise and utility of our framework in diverse scenarios. The results contribute to the ongoing efforts in the AutoML field, suggesting new possibilities for efficiently handling complex multimodal data. This research represents a step towards developing more efficient and versatile tools in multimodal machine learning pipeline development, acknowledging the collaborative and ever-evolving nature of this field.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}