arXiv subjects

Walid Gaaloul

Publications and source records attributed to Walid Gaaloul.

6 recordsLinked to original sources

arXiv2026

Reliable Remediation Impact Prediction for Black-Box Security Ratings

Security rating platforms summarize externally observable cyber exposure and are expected to help organizations prioritize remediation. A platform may want to tell an organization how a candidate remediation action would affect its score, but repeatedly exposing exact score responses can reveal information about the hidden scoring engine. We propose a surrogate based approach for remediation score impact prediction that is designed to respect this opacity constraint. The surrogate predicts scores from organization configurations while explicitly representing checkpoint (i.e., a security check) applicability and the observed checkpoint set. A main challenge is that such predictions are not uniformly reliable: they depend on the amount and structure of the observable checkpoint evidence available for a given configuration. To address this, the approach combines applicability-aware surrogate construction, sensitivity analysis under controlled checkpoint restriction, a reliability layer for identifying unstable predictions, and score-impact prediction for supported remediation actions. Explicit modeling of checkpoint applicability is central throughout: it improves score prediction and provides the feature basis used by the reliability layer to identify unstable cases. We evaluate the approach on a real-world dataset of 5,188 organization configurations from a commercial security rating platform. The results show that the applicability-aware surrogate improves score prediction over simpler feature representations. For remediation, the surrogate predicts the score impact of supported actions, while the reliability layer helps identify cases in which these predicted impacts should be interpreted cautiously.

cs.CR↗

arXiv2026

Motivation is Something You Need

This work introduces a novel training paradigm that draws from affective neuroscience. Inspired by the interplay of emotions and cognition in the human brain and more specifically the SEEKING motivational state, we design a dual-model framework where a smaller base model is trained continuously, while a larger motivated model is activated intermittently during predefined "motivation conditions". The framework mimics the emotional state of high curiosity and anticipation of reward in which broader brain regions are recruited to enhance cognitive performance. Exploiting scalable architectures where larger models extend smaller ones, our method enables shared weight updates and selective expansion of network capacity during noteworthy training steps. Empirical evaluation on the image classification task demonstrates that, not only does the alternating training scheme efficiently and effectively enhance the base model compared to a traditional scheme, in some cases, the motivational model also surpasses its standalone counterpart despite seeing less data per epoch. This opens the possibility of simultaneously training two models tailored to different deployment constraints with competitive or superior performance while keeping training cost lower than when training the larger model.

cs.AI↗

arXiv2026

Semantic Labeling for Third-Party Cybersecurity Risk Assessment: A Semi-Supervised Approach to Intent-Aware Question Retrieval

Third-Party Risk Assessment (TPRA) relies on large repositories of cybersecurity compliance questions used to assess external suppliers against standards such as ISO/IEC 27001 and NIST. In practice, not all questions are relevant for a specific supplier and selecting questions for a given assessment context remains a manual and time-consuming task. Existing question retrieval approaches based on lexical or semantic similarity can identify topically related questions, but they often fail to capture the underlying assessment intent, including control domain and evaluation scope. To address this limitation, we investigate whether an explicit semantic label space can improve intent-aware TPRA question selection. In particular, we separate label space discovery from large-scale label assignment. We start by discovering overlapping clusters of semantically similar questions and then exploit LLMs to assign unique labels for each cluster. Second, we propagate labels through k-nearest neighbors (kNN) for a larger-scale question annotation. Question retrieval is finally achieved by similarity measure of the query with respect to the extracted labels instead of the questions themselves. This reduces repeated LLM calls while preserving label consistency. Experimental results show that the proposed semi-supervised framework reduces labeling cost and runtime compared with per-question LLM annotation while maintaining label quality and improving efficiency. Furthermore, label-based retrieval achieves better alignment with cybersecurity control domains and assessment scope than similarity-based retrieval, highlighting the value of semantic labels as an intermediate representation.

cs.CR↗

arXiv2025

On the Marriage of Theory and Practice in Data-Aware Business Processes via Low-Code

In recent years, there has been a growing interest in the verification of business process models. Despite their lack of formal characterization, these models are widely adopted in both industry and academia. To address this issue, formalizing the execution semantics of business process modeling languages is essential. Since data and process are two facets of the same coin, and data are critical elements in the execution of process models, this work introduces Proving an eXecutable BPMN injected with data, BPMN-ProX. BPMN-ProX is a low-code testing framework that significantly enhances the verification of data-aware BPMN. This low-code platform helps bridge the gap between non-technical experts and professionals by proposing a tool that integrates advanced data handling and employs a robust verification mechanism through state-of-the-art model checkers. This innovative approach combines theoretical verification with practical modeling, fostering more agile, reliable, and user-centric business process management.

cs.SE↗

arXiv2025

BTC-SAM: Leveraging LLMs for Generation of Bias Test Cases for Sentiment Analysis Models

Sentiment Analysis (SA) models harbor inherent social biases that can be harmful in real-world applications. These biases are identified by examining the output of SA models for sentences that only vary in the identity groups of the subjects. Constructing natural, linguistically rich, relevant, and diverse sets of sentences that provide sufficient coverage over the domain is expensive, especially when addressing a wide range of biases: it requires domain experts and/or crowd-sourcing. In this paper, we present a novel bias testing framework, BTC-SAM, which generates high-quality test cases for bias testing in SA models with minimal specification using Large Language Models (LLMs) for the controllable generation of test sentences. Our experiments show that relying on LLMs can provide high linguistic variation and diversity in the test sentences, thereby offering better test coverage compared to base prompting methods even for previously unseen biases.

cs.CL↗

arXiv2024

A Novel Approach to Process Discovery with Enhanced Loop Handling

Automated process discovery from event logs is a key component of process mining, allowing companies to acquire meaningful insights into their business processes. Despite significant research, present methods struggle to balance important quality dimensions: fitness, precision, generalization, and complexity, but is limited when dealing with complex loop structures. This paper introduces Bonita Miner, a novel approach to process model discovery that generates behaviorally accurate Business Process Model and Notation (BPMN) diagrams. Bonita Miner incorporates an advanced filtering mechanism for Directly Follows Graphs (DFGs) alongside innovative algorithms designed to capture concurrency, splits, and loops, effectively addressing limitations of balancing as much as possible these four metrics, either there exists a loop, which challenge in existing works. Our approach produces models that are simpler and more reflective of the behavior of real-world processes, including complex loop dynamics. Empirical evaluations using real-world event logs demonstrate that Bonita Miner outperforms existing methods in fitness, precision, and generalization, while maintaining low model complexity.

cs.DB↗