DataSemantics: Automatic Data Integration Powered by LLMs

Hello! We are researchers from the Converging Technologies lab at Fujitsu Research. We are presenting a novel semi-automated solution to the problem of data conversion and integration into desired structures and formats. In data-driven systems, integrating disparate data sources becomes challenging when incoming data doesn’t conform to the system’s data specifications. Despite advances in automated schema matching systems, data integration tasks involving complex semantic interrelationships still require users to manually identify and define elaborate transformations between datasets. This process consumes a huge amount of manual time and effort and remains a bottleneck in modern data integration workflows. Our DataSemantics technology employs an AI-driven human-in-the-loop system to automate the end-to-end data conversion. It uses LLMs to analyze semantic relationships and generate step-by-step transformation pipelines autonomously, while only requesting the user’s attention to resolve specific semantic ambiguities through its user interface.

Generative AI for Software Engineering #3: Test Specification Generation Technology

Hello. We are Taro Togawa and Takao Nakagawa from Artificial Intelligence Laboratory in Fujitsu Research.

To promote the use of generative AI at enterprises, Fujitsu has developed a generative AI framework for enterprises that can flexibly respond to diverse and changing corporate needs and easily comply with the vast amount of data held by a company and laws and regulations. The framework was successively launched in July 2024 as part of Fujitsu Kozuchi (R&D)'s AI service lineup. In this article, we will focus on the transformation in system operations and maintenance brought about by generative AI, and introduce Test Specification Generation Technology, which automates the creation of test cases from existing design documents.

Introducing "Fujitsu Causal AI" (Total of 3 Parts) #1 Causal Action Optimization Technology

Hello. We are Takagi, Okajima, Koyanagi, and Ogawa from the Artificial Intelligence Research Laboratory.

Fujitsu has developed "Fujitsu Causal AI" to support data-driven decision-making in enterprises. This technology analyzes causal relationships from corporate data and uses them to recommend actions that are most effective and have no negative impact, based on a wide range of information.

Generative AI for Software Engineering #2: Design Review Assistant (Presented at SANER 2025)

Hello. I'm Takasaburo Fukuda from Artificial Intelligence Laboratory in Fujitsu Research.

To promote the use of generative AI at enterprises, Fujitsu has developed a generative AI framework for enterprises that can flexibly respond to diverse and changing corporate needs and easily comply with the vast amount of data held by a company and laws and regulations. The framework was successively launched in July 2024 as part of Fujitsu Kozuchi (R&D)'s AI service lineup. In this article, we will focus on the transformation in system development and operations brought about by generative AI, and introduce Design Review Assistant, which automates the review of software design documents.

Generative AI for Software Engineering #1: Identifying the Cause of Failures by Reviewing Specifications and Source Code – Introduction to Code Specification Consistency Analysis

Hello. I'm Oura from Artificial Intelligence Laboratory in Fujitsu Research.

To promote the use of generative AI at enterprises, Fujitsu has developed a generative AI framework for enterprises that can flexibly respond to diverse and changing corporate needs and easily comply with the vast amount of data held by a company and laws and regulations. The framework was successively launched in July 2024 as part of Fujitsu Kozuchi (R&D)'s AI service lineup. In this article, we will focus on the transformation in system development and operations brought about by generative AI, and introduce Code Specification Consistency Analysis, which automates the identification of program failure causes.

Is GPT-5 Easier to Jailbreak — or Are We Assessing It Wrong? A Comprehensive Assessment of GPT-5 Security Risks Using Fujitsu’s LLM Vulnerability Scanner

Hello, we are Omer and Roman from the Generative AI Trust Research team at Fujitsu’s Data & Security Research Laboratory. We’re excited to share our latest work: the first comprehensive security evaluation of GPT-5, conducted using our Fujitsu's LLM Vulnerability Scanner. This report dives deep into the security posture of GPT-5 and its sibling models, going beyond surface-level jailbreak prompts to examine data leakage and agentic misuse. We also apply a critical lens on how OpenAI’s new alignment strategies are reshaping red-teaming and security standards.

Our key finding: GPT-5’s "Safe-completions" approach to the safety alignment *1, designed to maximize helpfulness within policy boundaries, changes the model’s behavior, and also requires the AI security community to redefine how red-teaming should be conducted. While GPT-5 Full demonstrates strong reasoning, higher robustness in agentic environments, and reduced data leakage, it shows greater susceptibility to malicious prompts compared to GPT-4o, which still relies on an earlier alignment strategy - “refusal-first” *2.

Early reviews of GPT-5 *3, *4 have already claimed it is less safe than GPT-4, pointing to jailbreak successes and toxic outputs. But is GPT-5 truly weaker - or are today’s red-teaming methods, built around refusal detection, missing the bigger picture? We argue that what looks like regression may actually reflect a mismatch between evaluation methods and GPT-5’s new safety alignment paradigm.

This shift highlights a blind spot for current testing. To properly assess GPT-5 ‘Safe-Completions’, red-teaming must evolve beyond refusal testing and instead evaluate how “safe” completions can still enable misuse - whether through partial disclosures, or inconsistent policy application across contexts.

Read on for a full breakdown of our evaluation methodology, key results, and practical recommendations.

*1:From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Training

*2:GPT-4o System Card

*3:GPT-5 Jailbreak with Echo Chamber and Storytelling

*4:GPT-5 Under Fire: Red Teaming OpenAI’s Latest Model Reveals Surprising Weaknesses

FUJITSU-MONAKA team from Fujitsu Research India participated in ISC2025 poster exhibition

Namaskara! We are software engineers in the FUJITSU-MONAKA Software R&D team at Fujitsu Research of India Pvt Ltd (FRIPL). Our goal is to expand and optimize the HPC-AI software ecosystem for Arm CPUs, with special focus maximizing performance for FUJITSU-MONAKA together with our counterparts in Fujitsu Research Japan. Our work spans various software verticals, including databases, machine learning frameworks, deep learning and GenAI frameworks, and confidential computing. Recently, the three of us got an opportunity to present some of our work at the ISC25 conference held in Germany. In this article, we would like to share our experience of this event and the things we learned from it.

Author: Nishant Prabhu, Shreyas K Shankar, Divya Kotadiya

Introducing Fujitsu KG Enhanced RAG #5 Fujitsu KG Enhanced RAG for LA (Log Analysis)

Hello. I'm Supriya from Fujitsu Research of India, and I'm Oura from the Artificial Intelligence Laboratory.

To promote the use of generative AI at enterprises, Fujitsu has developed a generative AI framework for enterprises that can flexibly respond to diverse and changing corporate needs and easily comply with the vast amount of data held by a company and laws and regulations. The framework was successively launched in July 2024 as part of Fujitsu Kozuchi (R&D)'s AI service lineup.

Hybrid Graphs for Table-and-Text based Question Answering using LLMs - accepted at NAACL 2025

Introduction

Hello! I am Ankush Agarwal, a Researcher at the Artificial Intelligence Laboratory of Fujitsu Research India. My research focuses on knowledge graphs and deep learning, particularly their applications in the enterprise domain.

Toward Reliable and Efficient Characterization of Quantum Operation’s Accuracy

About this post

Thank you for visiting this post. I'm Takanori Sugiyama, a principal researcher at Fujitsu Research of Japan. I belong to an experimental team of superconducting quantum computer as a theorist. I gave a poster presentation about my research progress at an event, Fujitsu Quantum Day 2025 Japan, on March 28, 2025. www.fujitsu.com In this post, I'm going to briefly explain the content of my poster, which is about a characterization of gate operations used in a quantum computer. You can see more detailed and technical explanation on our recent preprint. arxiv.org

Improving Variational Algorithms through hybrid gradient computation methods: Pathway for training large-scale quantum machine learning models

Hello, I am Rahul Bhowmick from the Quantum team at Fujitsu Research India Private Limited.

Contextual Quantum Neural Networks for Portfolio and Index Forecasting

Hello, I am Hannes LEIPOLD, a researcher at Fujitsu Research of America (FRA) working on quantum computing. Fujitsu has been developing quantum technologies as a global effort, involving its research laboratories in Japan, Europe, India, and North America.

In this article, I will discuss a recent preprint we have released, which was presented as an oral talk at the American Physical Society’s 2025 March Meeting in Anaheim, California, U.S. on March 17th as well as a poster presentation at Fujitsu’s Quantum Day held at the Uvance Kawasaki Tower in Kawasaki, Japan on March 28th.

Cutting and knitting of quantum circuits

This is Vicente P. Soloviev and Michal Krompiec, from Quantum Applications Research group, part of the Quantum Lab at Fujitsu. In this post we give an overview of our recent results on the development of an automatic framework for circuit cutting (QuantCut) and its application to portfolio diversification for the S&P 500 stock market.

Benchmarking Hardware-Friendly Ansätze for Organic Molecules on FUJITSU Quantum Simulator

Hello, I am Carlos BISTAFA, a researcher at the Quantum Laboratory, Fujitsu Research. Fujitsu has been exploring quantum computing at all levels, from developing the necessary hardware to creating associated software, as well as investigating applications of this groundbreaking technology.

In this article, I will discuss the results we obtained from our research collaboration with Fujifilm Corporation, which were presented at the 2025 edition of our event, "Fujitsu Quantum Day," held in March here in our home city, Kawasaki.