Science & Tech · Cybersecurity · 1 hr ago
AI system finds 17 security flaws in tests of 50 mobile apps
South Korea’s Financial Security Institute has developed an AI-based method to find security risks in mobile apps.
The research was accepted for the main research track at ISSTA 2026, an international software engineering conference.
The method examines app code as well as what apps do while running and how information moves through them.
This matters because apps use outside software libraries and operating system features, so code alone may not reveal every risk.
In tests of 50 real mobile apps, the researchers found 17 security flaws.
The institute plans to use the research to build an AI-based framework for checking mobile apps in the financial sector.
It says it will update the detection method using findings from those checks and new threat cases.
The Financial Security Institute said its AI-based mobile app security detection technology found 17 vulnerabilities in tests of 50 real mobile apps.
The technology analyzes app code as well as behavior and information flows during execution.
The institute plans to develop an AI-based inspection framework for security checks of financial-sector mobile apps.
The research was accepted as a regular paper in the main research track of ISSTA 2026.
Researchers presented the findings at the conference in California from October 4 to 9.
- Who
- The Financial Security Institute developed the technology. Song Seong-hyun, a team leader at the institute, was the paper’s first author.
- What
- An AI-based system identified 17 security vulnerabilities in tests of 50 mobile apps.
- When
- The institute announced the research on October 12, 2026. It was presented at ISSTA 2026 from October 4 to 9.
- Where
- The research was presented at ISSTA 2026 in California, United States.
- Why
- The technology is intended to detect mobile app security risks and support security checks in the financial sector.
This story does not have two clearly opposing sides.
This research shows that the Financial Security Institute has the expertise to research security threats directly and develop technologies to detect them.
We will continue to develop outstanding research results into security technologies that can be applied in the financial sector and provide practical help in improving the security levels of financial companies.
Researchers presented the findings at ISSTA 2026 in California.
The Financial Security Institute announced that the research had been accepted as a regular paper at ISSTA 2026.
- Apps tested
- 50 real mobile apps
- Vulnerabilities found
- 17
- Conference
- ISSTA 2026
- Conference location
- California, United States
- Conference dates
- October 4–9, 2026
- Planned use
- Security checks of financial-sector mobile apps
Sources
Related news
New characters let lookalike domains bypass some browser checks
Hackers use Bing redirects in Google ads to promote fake Claude installers
Amazon Bedrock flaw exposed AI agent credentials and source code
AhnLab to Enable AI and Internet Access on Research Foundation Work Network
US seizes two China-linked hacking tools used against critical infrastructure
Canadian cybersecurity negotiator arrested in ShinyHunters investigation
Anthropic offers free AI vulnerability scans to open-source projects
FBI arrests another suspect linked to ShinyHunters jobs-site breach
119 databases from Russian companies published online in first nine months of 2026
Study finds car apps share drivers’ data with advertising and analytics firms
AI-assisted attacks hit South Korean financial institutions
