Elastic, 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 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 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.
“The rapid adoption and ongoing innovation in LLMs has increased the integration of this technology into business applications, creating unprecedented opportunities for adversaries to exploit vulnerabilities in emerging technologies,” said Asjad Athick, Cyber Security Lead, Asia Pacific and Japan at Elastic. “Standardizing data ingestion and analysis enhances industry safety, aligning with our research goals. Our detection rule repository now incorporates detections for LLMs, allowing customers to monitor threats efficiently and stay on top of issues that may affect their environment.”