Risk Management · Security and Compliance
As Italy's national agency for workplace health and safety, INAIL holds sensitive personal information and needed stronger defenses against growing phishing campaigns, sophisticated malware, and potential data breaches, along with more current threat intelligence and automated analysis.
Reported impact
INAIL improved the effectiveness and timeliness of threat detection and response, increased automated sharing of threat data, avoided malware infection and work-disruption costs, and maintained service continuity during the COVID-19 period.
INAIL worked with DXC to implement an automated cyber-threat intelligence and analysis platform centered on IOC ingestion, search, and machine-learning scoring. Upstream, open-source intelligence sources and multiple security intelligence engines feed threat data, email/domain/user lookups, and suspicious attachment evidence into leading security software and a search engine. MineMeld aggregates indicators of compromise from multiple sources and converts them into consistent configuration lists that INAIL's security workflow can redistribute to downstream security tools. For analysis, classifier systems and a machine learning model extract characteristics from domains and URLs to perform predictive reputation analysis and phishing detection at scale, including automated analysis on millions of URLs and domains. The solution is served through an external integration layer for technical users and a self-service malware analysis solution for 11,000 nontechnical users; the source does not name a separate storage product, so normalized threat data appears to be managed within the workflow while exchanges with other national security bodies are automated.
Open-source intelligence sources and security intelligence engines supply IOC and reputation data to leading security software, the search engine, and MineMeld. The platform normalizes indicators, runs classifier systems and a machine learning model on domains and URLs, then redistributes vetted IOC lists to INAIL's security tools. Technical users access outputs through the external integration layer, while employees use the malware analysis interface for self-service attachment checks.
"AI and machine learning technologies are then deployed to carry out automated security analysis on millions of specific URLs and domains scored as potential security threats."
"However, INAIL did not experience any service interruptions related to COVID-19."
"In the face of growing phishing attacks and highly sophisticated malware, INAIL is at the forefront of preventing data breaches."
"Information on IOCs is aggregated by generating configuration lists so the data can be processed by software such as MineMeld"
"Two versions of the solution have been released: an external integration layer for technical users, and an easy-to-use malware analysis solution provided to INAIL’s 11,000 nontechnical users"
"Using a machine learning model, INAIL performs predictive reputation analysis based on extraction of unique characteristics of domains and URLs."
"open-source intelligence sources are combined with leading security software to collect information on cyber threats and integrate the data into INAIL’s security workflow."
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
AWS Sample Apr 15, 2024 InfoCert Training and deploying these models was a lengthy, costly process, which limited access to this set of capabilities to larger companies. While InfoCert was searching for a way to streamline such ML integrations, AWS… Additionally, InfoCert expects to reduce financial overhead by 80 percent for startup, development, and… Amazon Bedrock 
OpenAI Sample Oct 14, 2026 SentinelOne SentinelOne needed to reverse engineer sophisticated malware far faster than specialist researchers could do manually so it could investigate more samples, spot relationships across threats, and extend scarce cyber… 8 hours to reverse-engineer malware, down from 4–6 weeks OpenAI Daybreak · OpenAI models 
Google Cloud Sample Archived · Sep 17, 2026 Parsewise For risk specialists in the financial services and insurance industries, reading can feel like a full-time job. Whether assessing an insurance claim or approving a loan, these subject matter experts must search through… 29% lower error rate than best-performing LLM on grounded-reasoning benchmark Gemini · Gemini 3.0 Flash · Gemini 3.5 Flash 
