Skip to content
NewA calmer, faster ZeroHour

DARPA Selects Xint to Use AI in Securing Military Messaging Apps

SecurityWeekby Kevin Townsend ()3 min read3 · 2 reads
AI summary · glm-5.3Summaries by Vani AI

DARPA selected AIxCC winner Xint to autonomously analyze and patch vulnerabilities in Department of War messaging apps like Signal.

DARPA selected Xint, a company that emerged from Theori and was one of three winners of the two-year, $29.5 million AI Cyber Challenge, to apply autonomous AI application security to Department of War messaging applications. Xint uses frontier LLMs to analyze source code and reverse-engineered binaries, triage vulnerabilities by attacker accessibility, and generate patches; it launched a compiled-binary supply chain analysis service in September 2026. The technology is offered as a SaaS product to commercial customers. CTO Andrew Wesie noted on-premises deployments remain difficult because the latest OpenAI and Anthropic models cannot run in customer data centers.

Key facts
  • DARPA picked AIxCC winner Xint to secure Department of War messaging apps
  • Xint uses frontier LLMs to analyze source code and reverse-engineer binaries
  • System triages vulnerabilities by attacker accessibility and auto-generates patches
  • Xint launched compiled-binary supply chain analysis SaaS in September 2026
Analyze this story with Vani AIImpact, who is affected and what defenders should do, in a new chat

From the original article

3 min read at securityweek.com

The AIxCC competition winner will analyze messaging app code and compiled binaries for vulnerabilities, with technology that could also help commercial customers secure their software. The post DARPA Selects Xint to Use AI in Securing Military Messaging Apps appeared first on SecurityWeek.

SecurityWeek

By Kevin Townsend · securityweek.com

Read the full article at SecurityWeek

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.