Product controls and SOC countermeasures to securely adopt LLMs

Elastic (NYSE: ESTC), the leading Search AI company, announced LLM Safety Assessment: The Definitive Guide on Avoiding Risk and Abuses, the latest research issued by Elastic Security Labs. The LLM Safety Assessment explores large language model (LLM) safety and provides attack mitigation best practices and suggested countermeasures for LLM abuses.

Generative AI and LLM implementations have become widely adopted over the past 18 months, with some companies pushing to implement them as quickly as possible. This has expanded the attack surface and left developers and security teams without clear guidance on how to adopt emerging LLM technology safely.

“For all their potential, broad LLM adoption has been met with unease by enterprise leaders, seen as yet another doorway for malicious actors to gain access to private information or a foothold in their IT ecosystems,” said Jake King, head of threat and security intelligence at Elastic. “Publishing open detection engineering content is in Elastic’s DNA. Security knowledge should be for everyone—safety is in numbers. We hope that all organizations, whether Elastic customers or not, can take advantage of these new rules and guidance.”

The LLM Safety Assessment builds and expands on the Open Web Application Security Project (OWASP) research focused on the most common LLM attack techniques. The research includes crucial information security teams can use to protect their LLM implementations, including in-depth explanations of risks, best practices and suggested countermeasures to mitigate attacks. The countermeasures explored in the research cover different areas of the enterprise architecture — primarily in-product controls — that developers should adopt when building LLM-enabled applications and information security measures SOCs must add to verify and validate the secure usage of LLMs.

In addition to 1000+ detection rules already published and maintained on GitHub, Elastic Security Labs added an initial set of detections just for LLM abuses. These new rules are an example of the out-of-box detection rules now included to detect LLM abuses.

“Normalizing and standardizing how data is ingested and analyzed makes the industry safer for everyone — which is exactly what this research intends to do,” said King. “Our detection rule repository helps customers monitor threats with confidence, as quickly as possible, and now includes LLM implementations. The rules are built and maintained publicly in alignment with Elastic’s dedication to transparency.”

Additional Resources

  • Blog: Elastic Advances LLM Security with Standardized Fields and Integrations
    • Explores the creation of integration workflows to reduce friction when assessing LLM security and details a new integration with AWS Bedrock
  • Blog: Embedding Security in LLM Workflows: Elastic's Proactive Approach
    • Highlights suggestions and examples of how to detect malicious LLM activities with ES|QL, and proposes a proxy based telemetry solution.
  • Blog: Accelerating Elastic detection tradecraft with LLMs
    • Focuses on Elastic Security Labs’ dedication to LLM research in the context of streamlining detection workflows with generative AI

About Elastic

Elastic (NYSE: ESTC), the Search AI Company, enables everyone to find the answers they need in real-time using all their data, at scale. Elastic’s solutions for search, observability and security are built on the Elastic Search AI Platform, the development platform used by thousands of companies, including more than 50% of the Fortune 500. Learn more at elastic.co.

Elastic and associated marks are trademarks or registered trademarks of Elastic N.V. and its subsidiaries. All other company and product names may be trademarks of their respective owners.

Candace Metoyer PR-team@elastic.co

Elastic NV (NYSE:ESTC)
Historical Stock Chart
Von Apr 2024 bis Mai 2024 Click Here for more Elastic NV Charts.
Elastic NV (NYSE:ESTC)
Historical Stock Chart
Von Mai 2023 bis Mai 2024 Click Here for more Elastic NV Charts.