arXiv subjects

Fuyuki Ishikawa

Publications and source records attributed to Fuyuki Ishikawa.

At least 19 recordsLinked to original sources

arXiv2026

RepTran: Search-Based Repair of Transformer Models

To ensure the overall quality of AI-enabled software, not only traditional software components but also AI components need to be tested and repaired. Among AI components, Transformer models are increasingly integrated into software systems, which makes their misbehaviors critical. Although prior work in the software engineering community has proposed deep neural network (DNN) repair methods, most overlook Transformer-specific structures. We propose RepTran, a search-based repair method for Transformer models. It targets their feed-forward networks (FFNs), which play a central role in the architecture. RepTran identifies suspicious weights by combining two types of scores: a variance-based neuron score and an existing bidirectional score. It then iteratively optimizes these weights using differential evolution. Our evaluation includes 18 fault benchmarks constructed from CIFAR-100 and Tiny-ImageNet. We compare RepTran against three baselines: random weight selection, Arachne (a state-of-the-art DNN repair method), and ArachneW, which enables Arachne to control the number of selected weights. RepTran achieved an average repair rate of 74.7%, statistically outperforming random selection and Arachne across all benchmarks. Effect size analysis revealed that RepTran achieved higher repair rates than ArachneW regardless of the number of selected weights. These results suggest that RepTran is effective for enhancing the reliability of AI-enabled software.

cs.SE↗

arXiv2026

Safety Case Patterns for VLA-based driving systems: Insights from SimLingo

Vision-Language-Action (VLA)-based driving systems represent a significant paradigm shift in autonomous driving since, by combining traffic scene understanding, linguistic interpretation, and action generation, these systems enable more flexible, adaptive, and instruction-responsive driving behaviors. However, despite their growing adoption and potential to support socially responsible autonomous driving as well as understanding high-level human instructions, VLA-based driving systems may exhibit new types of hazardous behaviors. For instance, the integration of open-ended natural language inputs (e.g., user or navigation instructions) into the multimodal control loop may lead to unpredictable and unsafe behaviors that could endanger vehicle occupants and pedestrians. Hence, assuring the safety of these systems is crucial to help build trust in their operations. To support this, we propose a novel safety case design approach called RAISE. Our approach introduces novel patterns tailored to instruction-based driving systems such as VLA-based driving systems, an extension of Hazard Analysis and Risk Assessment (HARA) detailing safe scenarios and their outcomes, and a design technique to create the safety cases of VLA-based driving systems. A case study on SimLingo illustrates how our approach can be used to construct rigorous, evidence-based safety claims for this emerging class of autonomous driving systems.

cs.RO↗

arXiv2026

Software Testing in the Quantum World

Quantum computing offers significant speedups for simulating physical, chemical, and biological systems, and for optimization and machine learning. As quantum software grows in complexity, the classical simulation of quantum computers, which has long been essential for quality assurance, becomes infeasible. This shift requires new quality-assurance methods that operate directly on real quantum computers. This paper presents the key challenges in testing large-scale quantum software and offers software engineering perspectives for addressing them.

cs.SE↗

arXiv2025

Situating AI Agents in their World: Aspective Agentic AI for Dynamic Partially Observable Information Systems

Agentic LLM AI agents are often little more than autonomous chatbots: actors following scripts, often controlled by an unreliable director. This work introduces a bottom-up framework that situates AI agents in their environment, with all behaviors triggered by changes in their environments. It introduces the notion of aspects, similar to the idea of umwelt, where sets of agents perceive their environment differently to each other, enabling clearer control of information. We provide an illustrative implementation and show that compared to a typical architecture, which leaks up to 83% of the time, aspective agentic AI enables zero information leakage. We anticipate that this concept of specialist agents working efficiently in their own information niches can provide improvements to both security and efficiency.

cs.AI↗

arXiv2025

FairFLRep: Fairness aware fault localization and repair of Deep Neural Networks

Deep neural networks (DNNs) are being utilized in various aspects of our daily lives, including high-stakes decision-making applications that impact individuals. However, these systems reflect and amplify bias from the data used during training and testing, potentially resulting in biased behavior and inaccurate decisions. For instance, having different misclassification rates between white and black sub-populations. However, effectively and efficiently identifying and correcting biased behavior in DNNs is a challenge. This paper introduces FairFLRep, an automated fairness-aware fault localization and repair technique that identifies and corrects potentially bias-inducing neurons in DNN classifiers. FairFLRep focuses on adjusting neuron weights associated with sensitive attributes, such as race or gender, that contribute to unfair decisions. By analyzing the input-output relationships within the network, FairFLRep corrects neurons responsible for disparities in predictive quality parity. We evaluate FairFLRep on four image classification datasets using two DNN classifiers, and four tabular datasets with a DNN model. The results show that FairFLRep consistently outperforms existing methods in improving fairness while preserving accuracy. An ablation study confirms the importance of considering fairness during both fault localization and repair stages. Our findings also show that FairFLRep is more efficient than the baseline approaches in repairing the network.

cs.LG↗

arXiv2025

CLEAR: Cue Learning using Evolution for Accurate Recognition Applied to Sustainability Data Extraction

Large Language Model (LLM) image recognition is a powerful tool for extracting data from images, but accuracy depends on providing sufficient cues in the prompt - requiring a domain expert for specialized tasks. We introduce Cue Learning using Evolution for Accurate Recognition (CLEAR), which uses a combination of LLMs and evolutionary computation to generate and optimize cues such that recognition of specialized features in images is improved. It achieves this by auto-generating a novel domain-specific representation and then using it to optimize suitable textual cues with a genetic algorithm. We apply CLEAR to the real-world task of identifying sustainability data from interior and exterior images of buildings. We investigate the effects of using a variable-length representation compared to fixed-length and show how LLM consistency can be improved by refactoring from categorical to real-valued estimates. We show that CLEAR enables higher accuracy compared to expert human recognition and human-authored prompts in every task with error rates improved by up to two orders of magnitude and an ablation study evincing solution concision.

cs.CV↗

arXiv2025

An Experience Report on Regression-Free Repair of Deep Neural Network Model

Systems based on Deep Neural Networks (DNNs) are increasingly being used in industry. In the process of system operation, DNNs need to be updated in order to improve their performance. When updating DNNs, systems used in companies that require high reliability must have as few regressions as possible. Since the update of DNNs has a data-driven nature, it is difficult to suppress regressions as expected by developers. This paper identifies the requirements for DNN updating in industry and presents a case study using techniques to meet those requirements. In the case study, we worked on satisfying the requirement to update models trained on car images collected in Fujitsu assuming security applications without regression for a specific class. We were able to suppress regression by customizing the objective function based on NeuRecover, a DNN repair technique. Moreover, we discuss some of the challenges identified in the case study.

cs.SE↗

arXiv2024

SCAPE: Searching Conceptual Architecture Prompts using Evolution

Conceptual architecture involves a highly creative exploration of novel ideas, often taken from other disciplines as architects consider radical new forms, materials, textures and colors for buildings. While today's generative AI systems can produce remarkable results, they lack the creativity demonstrated for decades by evolutionary algorithms. SCAPE, our proposed tool, combines evolutionary search with generative AI, enabling users to explore creative and good quality designs inspired by their initial input through a simple point and click interface. SCAPE injects randomness into generative AI, and enables memory, making use of the built-in language skills of GPT-4 to vary prompts via text-based mutation and crossover. We demonstrate that compared to DALL-E 3, SCAPE enables a 67% improvement in image novelty, plus improvements in quality and effectiveness of use; we show that in just three iterations SCAPE has a 24% image novelty increase enabling effective exploration, plus optimization of images by users. We use more than 20 independent architects to assess SCAPE, who provide markedly positive feedback.

cs.NE↗

arXiv2024

Formal Modelling of Safety Architecture for Responsibility-Aware Autonomous Vehicle via Event-B Refinement

Ensuring the safety of autonomous vehicles (AVs) is the key requisite for their acceptance in society. This complexity is the core challenge in formally proving their safety conditions with AI-based black-box controllers and surrounding objects under various traffic scenarios. This paper describes our strategy and experience in modelling, deriving, and proving the safety conditions of AVs with the Event-B refinement mechanism to reduce complexity. Our case study targets the state-of-the-art model of goal-aware responsibility-sensitive safety to argue over interactions with surrounding vehicles. We also employ the Simplex architecture to involve advanced black-box AI controllers. Our experience has demonstrated that the refinement mechanism can be effectively used to gradually develop the complex system over scenario variations.

cs.SE↗

arXiv2023

Using a Variational Autoencoder to Learn Valid Search Spaces of Safely Monitored Autonomous Robots for Last-Mile Delivery

The use of autonomous robots for delivery of goods to customers is an exciting new way to provide a reliable and sustainable service. However, in the real world, autonomous robots still require human supervision for safety reasons. We tackle the realworld problem of optimizing autonomous robot timings to maximize deliveries, while ensuring that there are never too many robots running simultaneously so that they can be monitored safely. We assess the use of a recent hybrid machine-learningoptimization approach COIL (constrained optimization in learned latent space) and compare it with a baseline genetic algorithm for the purposes of exploring variations of this problem. We also investigate new methods for improving the speed and efficiency of COIL. We show that only COIL can find valid solutions where appropriate numbers of robots run simultaneously for all problem variations tested. We also show that when COIL has learned its latent representation, it can optimize 10% faster than the GA, making it a good choice for daily re-optimization of robots where delivery requests for each day are allocated to robots while maintaining safe numbers of robots running at once.

cs.NE↗

arXiv2022

Goal-Aware RSS for Complex Scenarios via Program Logic

We introduce a goal-aware extension of responsibility-sensitive safety (RSS), a recent methodology for rule-based safety guarantee for automated driving systems (ADS). Making RSS rules guarantee goal achievement -- in addition to collision avoidance as in the original RSS -- requires complex planning over long sequences of manoeuvres. To deal with the complexity, we introduce a compositional reasoning framework based on program logic, in which one can systematically develop RSS rules for smaller subscenarios and combine them to obtain RSS rules for bigger scenarios. As the basis of the framework, we introduce a program logic dFHL that accommodates continuous dynamics and safety conditions. Our framework presents a dFHL-based workflow for deriving goal-aware RSS rules; we discuss its software support, too. We conducted experimental evaluation using RSS rules in a safety architecture. Its results show that goal-aware RSS is indeed effective in realising both collision avoidance and goal achievement.

cs.RO↗

arXiv2022

Practical Insights of Repairing Model Problems on Image Classification

Additional training of a deep learning model can cause negative effects on the results, turning an initially positive sample into a negative one (degradation). Such degradation is possible in real-world use cases due to the diversity of sample characteristics. That is, a set of samples is a mixture of critical ones which should not be missed and less important ones. Therefore, we cannot understand the performance by accuracy alone. While existing research aims to prevent a model degradation, insights into the related methods are needed to grasp their benefits and limitations. In this talk, we will present implications derived from a comparison of methods for reducing degradation. Especially, we formulated use cases for industrial settings in terms of arrangements of a data set. The results imply that a practitioner should care about better method continuously considering dataset availability and life cycle of an AI system because of a trade-off between accuracy and preventing degradation.

cs.LG↗

arXiv2022

NeuRecover: Regression-Controlled Repair of Deep Neural Networks with Training History

Systematic techniques to improve quality of deep neural networks (DNNs) are critical given the increasing demand for practical applications including safety-critical ones. The key challenge comes from the little controllability in updating DNNs. Retraining to fix some behavior often has a destructive impact on other behavior, causing regressions, i.e., the updated DNN fails with inputs correctly handled by the original one. This problem is crucial when engineers are required to investigate failures in intensive assurance activities for safety or trust. Search-based repair techniques for DNNs have potentials to tackle this challenge by enabling localized updates only on "responsible parameters" inside the DNN. However, the potentials have not been explored to realize sufficient controllability to suppress regressions in DNN repair tasks. In this paper, we propose a novel DNN repair method that makes use of the training history for judging which DNN parameters should be changed or not to suppress regressions. We implemented the method into a tool called NeuRecover and evaluated it with three datasets. Our method outperformed the existing method by achieving often less than a quarter, even a tenth in some cases, number of regressions. Our method is especially effective when the repair requirements are tight to fix specific failure types. In such cases, our method showed stably low rates (<2%) of regressions, which were in many cases a tenth of regressions caused by retraining.

cs.LG↗

arXiv2021

Robustifying Controller Specifications of Cyber-Physical Systems Against Perceptual Uncertainty

Formal reasoning on the safety of controller systems interacting with plants is complex because developers need to specify behavior while taking into account perceptual uncertainty. To address this, we propose an automated workflow that takes an Event-B model of an uncertainty-unaware controller and a specification of uncertainty as input. First, our workflow automatically injects the uncertainty into the original model to obtain an uncertainty-aware but potentially unsafe controller. Then, it automatically robustifies the controller so that it satisfies safety even under the uncertainty. The case study shows how our workflow helps developers to explore multiple levels of perceptual uncertainty. We conclude that our workflow makes design and analysis of uncertainty-aware controller systems easier and more systematic.

cs.SE↗

arXiv2021

Architecture-Guided Test Resource Allocation Via Logic

We introduce a new logic named Quantitative Confidence Logic (QCL) that quantifies the level of confidence one has in the conclusion of a proof. By translating a fault tree representing a system's architecture to a proof, we show how to use QCL to give a solution to the test resource allocation problem that takes the given architecture into account. We implemented a tool called Astrahl and compared our results to other testing resource allocation strategies.

cs.SE↗

arXiv2019

A Mutation-based Approach for Assessing Weight Coverage of a Path Planner

Autonomous cars are subjected to several different kind of inputs (other cars, road structure, etc.) and, therefore, testing the car under all possible conditions is impossible. To tackle this problem, scenario-based testing for automated driving defines categories of different scenarios that should be covered. Although this kind of coverage is a necessary condition, it still does not guarantee that any possible behaviour of the autonomous car is tested. In this paper, we consider the path planner of an autonomous car that decides, at each timestep, the short-term path to follow in the next few seconds; such decision is done by using a weighted cost function that considers different aspects (safety, comfort, etc.). In order to assess whether all the possible decisions that can be taken by the path planner are covered by a given test suite T, we propose a mutation-based approach that mutates the weights of the cost function and then checks if at least one scenario of T kills the mutant. Preliminary experiments on a manually designed test suite show that some weights are easier to cover as they consider aspects that more likely occur in a scenario, and that more complicated scenarios (that generate more complex paths) are those that allow to cover more weights.

cs.SE↗

arXiv2019

Adapting SQuaRE for Quality Assessment of Artificial Intelligence Systems

More and more software practitioners are tackling towards industrial applications of artificial intelligence (AI) systems, especially those based on machine learning (ML). However, many of existing principles and approaches to traditional systems do not work effectively for the system behavior obtained by training not by logical design. In addition, unique kinds of requirements are emerging such as fairness and explainability. To provide clear guidance to understand and tackle these difficulties, we present an analysis on what quality concepts we should evaluate for AI systems. We base our discussion on ISO/IEC 25000 series, known as SQuaRE, and identify how it should be adapted for the unique nature of ML and $\textit{Ethics guidelines for trustworthy AI}$ from European Commission. We thus provide holistic insights for quality of AI systems by incorporating the ML nature and AI ethics to the traditional software quality concepts.

cs.CY↗

arXiv2013

A Scalable Distributed Architecture for Network- and QoS-aware Service Composition

Service-Oriented Computing (SOC) enables the composition of loosely coupled service agents provided with varying Quality of Service (QoS) levels, effectively forming a multiagent system (MAS). Selecting a (near-)optimal set of services for a composition in terms of QoS is crucial when many functionally equivalent services are available. As the number of distributed services, especially in the cloud, is rising rapidly, the impact of the network on the QoS keeps increasing. Despite this and opposed to most MAS approaches, current service approaches depend on a centralized architecture which cannot adapt to the network. Thus, we propose a scalable distributed architecture composed of a flexible number of distributed control nodes. Our architecture requires no changes to existing services and adapts from a centralized to a completely distributed realization by adding control nodes as needed. Also, we propose an extended QoS aggregation algorithm that allows to accurately estimate network QoS. Finally, we evaluate the benefits and optimality of our architecture in a distributed environment.

cs.DC↗