Leidos introduces new AI platform to find, fix cybersecurity vulnerabilities

Rhea-AI Summary

Leidos (NYSE: LDOS) introduced Parcata™, a proprietary AI-driven cybersecurity platform designed to autonomously find and fix software vulnerabilities in government and commercial environments. The model-agnostic tool uses multiple large language models to accelerate detection in first- and third-party code and can patch zero-day issues in real time. Developed by the Kudu Dynamics team and validated through DARPA's AI Cyber Challenge, Parcata has been tested in internal exercises and is currently being applied to Leidos code prior to deployment. Leidos said this work supports its NorthStar 2030 strategy focused on AI-enabled capabilities at operational scale.

Market Context

Across tag-specific AI events, the average 24-hour move was -0.32%. Parcata adds to an established A...

Analysis

Across tag-specific AI events, the average 24-hour move was -0.32%. Parcata adds to an established AI-news record, while low short positioning and the active S-3ASR shelf frame risk context.

Key Figures

Announcement date: July 29, 2026

1 metrics

Announcement date July 29, 2026 Article publication

Previous AI Reports

5 past events · Latest: Jul 22 (Positive)

Same Type Pattern 5 events

Date	Event	Sentiment	24h Move	Catalyst
Jul 22	AI platform deployment	Positive	+2.9%	ServiceNow AI deployment targeted enterprise efficiency and support for approximately 50,000 employees.
Jul 09	AI logistics partnership	Positive	-0.5%	Rune partnership targeted predictive logistics and sustainment for Indo-Pacific military operations.
Mar 10	AI cyber partnership	Positive	-3.9%	Dropzone AI partnership targeted faster federal security operations and defensive AI deployments.
Feb 04	AI governance partnership	Positive	-0.7%	Trustible initiative targeted automated governance and accountable AI adoption across mission areas.
Jan 22	AI operations partnership	Positive	+0.7%	OpenAI partnership targeted generative and agentic AI integration into federal workflows.

24h Move is the share-price change in the day after each event; other market factors may also have contributed.

Pattern Detected

Leidos AI announcements produced mixed reactions, with two aligned positive moves and three divergences despite consistently positive announcement descriptions.

Key Terms

model-agnostic, large language models, zero-day vulnerabilities

3 terms

model-agnostic technical

"This next-generation, model-agnostic tool harnesses a diverse set of large language models"

An approach, tool, or test that works with any predictive or analytical model rather than depending on a single algorithm or vendor. For investors, model-agnostic methods let you compare, audit, and trust results across different forecasting systems—like using a universal charger that fits many phones—reducing reliance on one provider, making performance easier to validate, and lowering the risk that a single model’s quirks drive investment decisions.

large language models technical

"harnesses a diverse set of large language models to accelerate vulnerability detection"

Large language models are advanced AI systems trained on vast amounts of text to understand and generate human-like writing, like a very fast reader and writer that learns patterns in words and sentences. They matter to investors because they can change how companies operate—automating customer service, speeding analysis, cutting costs, creating new products—and they introduce risks around accuracy, security and regulation that can affect a firm’s revenue and reputation.

zero-day vulnerabilities technical

"can patch zero-day vulnerabilities in real time"

A zero-day vulnerability is a software or system flaw that attackers can exploit before the maker has issued a fix, like an unnoticed backdoor that the owner doesn’t yet know how to lock. Investors care because such hidden weaknesses can lead to data breaches, service outages, regulatory penalties and costly emergency fixes; those outcomes can damage revenue and reputation, causing sudden stock drops or increased liability for affected firms.

AI-generated analysis. How Rhea-AI works. Not financial advice.

See more from StockTitan in Google Search and AI answers. Adds StockTitan as a preferred source · opens Google

Add on Google Not now

RESTON, Va., July 29, 2026 /PRNewswire/ -- Government and commercial organizations could soon thwart potential cybersecurity threats by deploying Parcata™, a proprietary platform Leidos (NYSE: LDOS) has developed to autonomously find and fix software vulnerabilities.

This next-generation, model-agnostic tool harnesses a diverse set of large language models to accelerate vulnerability detection in first and third-party software and can patch zero-day vulnerabilities in real time.

"The use of AI by cyber adversaries has changed the game. We must detect and remediate before a breach," said Jason O'Connor, president of Leidos Intelligence. "Developed by our Kudu Dynamics team, with technology validated through DARPA's AI Cyber Challenge, Parcata will help organizations stay ahead of evolving threats. This tool will make sense out of the chaos and ensure the mission isn't dependent on any single frontier model."

The platform has demonstrated its capabilities through recent internal technical exercises and is being executed against Leidos code before it is deployed to mission environments.

This work aligns with Leidos' NorthStar 2030 strategy and its focus on AI-enabled capabilities and effects at operational scale across dynamic warfighting environments.  

For more information or to request a demo, visit leidos.com/parcata.

About Leidos 

Leidos is an industry and technology leader serving government and commercial customers with smarter, more efficient digital and mission innovations. Headquartered in Reston, Virginia, with more than 50,000 global employees, Leidos reported annual revenues of approximately $17.2 billion for the fiscal year ended January 2, 2026. For more information, visit www.Leidos.com.

Certain statements in this announcement constitute "forward-looking statements" within the meaning of the rules and regulations of the U.S. Securities and Exchange Commission (SEC). These statements are based on management's current beliefs and expectations and are subject to significant risks and uncertainties. These statements are not guarantees of future results or occurrences. A number of factors could cause our actual results, performance, achievements, or industry results to be different from the results, performance, or achievements expressed or implied by such forward-looking statements. These factors include, but are not limited to, the "Risk Factors" set forth in Leidos' Annual Report on Form 10-K for the fiscal year ended January 2, 2026, and other such filings that Leidos makes with the SEC from time to time. Readers are cautioned not to place undue reliance on such forward-looking statements, which speak only as of the date hereof. Leidos does not undertake to update forward-looking statements to reflect the impact of circumstances or events that arise after the date the forward-looking statements were made. 

Media Contact:

Victoria Piccoli
(571) 992-5142
victoria.piccoli@leidos.com 

 

View original content to download multimedia:https://www.prnewswire.com/news-releases/leidos-introduces-new-ai-platform-to-find-fix-cybersecurity-vulnerabilities-302837433.html

SOURCE Leidos Holdings, Inc.

FAQ

What is Leidos' Parcata AI cybersecurity platform announced on July 29, 2026 (NYSE: LDOS)?

Parcata is a proprietary AI platform from Leidos that autonomously finds and fixes software vulnerabilities. According to Leidos, it uses multiple large language models to accelerate vulnerability detection and remediation across first- and third-party software in government and commercial environments.

How does Leidos' Parcata platform use AI to improve cybersecurity for LDOS customers?

Parcata applies a diverse set of large language models to detect and remediate vulnerabilities. According to Leidos, the platform accelerates discovery of flaws, including zero-day issues, and can apply patches in real time across different software sources to help organizations counter evolving threats.

Can Leidos' Parcata platform fix zero-day vulnerabilities in real time for LDOS clients?

Yes, Parcata is designed to patch zero-day vulnerabilities in real time. According to Leidos, the model-agnostic tool autonomously detects and remediates software weaknesses, aiming to address emerging threats before they result in a breach for government and commercial users.

How was Leidos' Parcata AI platform validated before wider deployment (LDOS)?

Parcata’s technology was validated through DARPA's AI Cyber Challenge and internal technical exercises. According to Leidos, the platform is already being executed against Leidos code before deployment to mission environments, demonstrating its capabilities in realistic, operationally relevant scenarios.

How does Parcata support Leidos' NorthStar 2030 strategy for AI and cybersecurity?

Parcata aligns with Leidos' NorthStar 2030 strategy by advancing AI-enabled capabilities at operational scale. According to Leidos, the platform is intended to help secure dynamic warfighting and mission environments through autonomous vulnerability detection and repair across diverse software systems.

Is Leidos' Parcata platform dependent on a single AI model for cybersecurity performance?

No, Parcata is described as model-agnostic and not dependent on a single frontier model. According to Leidos, it harnesses a diverse set of large language models, aiming to provide resilience and flexibility as AI technologies and cyber threats continue to evolve.