Contrast Security Releases Assess Feature for LLMs to Protect Against AI Security Threats
The code security leader has introduced a new capability within its Secure Code Platform to address prompt injection, the top entry of the OWASP Top 10 for LLMs
Los Altos, CA — August 3, 2023 — Contrast Security (Contrast), the code security platform built for developers and trusted by security, today announced it will extend its market-leading application security testing (AST) platform to support testing of Large Language Models (LLMs) from OpenAI. In this first release, Contrast rules help teams that are developing software using the OpenAI application programming interface (API) set to identify and mitigate weaknesses that could expose an organization to prompt injection vulnerabilities: i.e., attacks involving injection of a prompt that deceives the application into executing unauthorized code.
Prompt injection was identified as the top risk for LLM applications by the just-released OWASP 10 Top for Large Language Model Applications project. Contrast has continued to support OWASP’s mission to improve Application Security (AppSec): In fact, Contrast’s Chief Product Officer Steve Wilson led the 400-person volunteer team that created the OWASP Top 10 for LLMs.
“As project lead for the new OWASP Top 10 for LLMs, I can say our group looked deeply at many attack vectors against LLMs. Prompt Injection repeatedly rose to the top of the list in our expert group voting for the most important vulnerability,” said Wilson. “Contrast is the first security solution to respond to this new industry standard list by delivering this capability. Organizations can now identify susceptible data flows to their LLMs, providing security with the visibility needed to identify risks and prevent unintended exposure.”
According to the OWASP Top 10 for LLMs, a prompt injection vulnerability allows an attacker to craft inputs that can manipulate the operation of a trusted LLM. This results in the LLM acting as a “confused deputy” on behalf of the attacker. Given the high degree of trust usually associated with an LLM's output, the manipulated responses may go unnoticed and may even be trusted by the user, allowing the attack to potentially poison search results, deliver incorrect or malicious responses, produce malicious code, circumvent content filters, or to leak sensitive data. Prompt injections can be introduced via various avenues, including websites, emails, documents or any other data source that an LLM might rely on.
Contrast is ideal for identifying all types of injection accurately, including this new form of AI prompt injection. Contrast uses runtime security to monitor actual application behavior and detect vulnerabilities, rather than scanning source code or simulating attacks. This approach is fast, easy and highly accurate, ensuring that developers are instantly notified of issues and provided all the information they need to correct problems. User input sent through OpenAI’s official Python API to an LLM in a Python agent-instrumented application triggers the prompt injection rule.
To learn more about how Contrast Assess provides the first security solution created to identify potential prompt injection vulnerabilities, please visit our website or schedule a demo.
About Contrast Security
Contrast is a world-leading code security platform company purposely built for developers to get secure code moving swiftly and trusted by security teams to protect business applications. Developers, security and operations teams quickly secure code across the complete Software Development Life Cycle (SDLC) with Contrast to protect against today’s targeted AppSec attacks.
Founded in 2014 by cybersecurity industry veterans, Contrast was established to replace legacy AppSec solutions that cannot protect modern enterprises. With today’s pressures to develop business applications at increasingly rapid paces, the Contrast Secure Code Platform defends and protects against full classes of Common Vulnerabilities and Exposures (CVEs). This allows security teams to avoid spending time focusing on false positives, leaving them more time to remediate true vulnerabilities faster. Contrast’s platform solutions for code assessment, testing, protection, serverless, supply chain, APIs and languages help enterprises achieve true DevSecOps transformation and compliance.
Contrast protects against major cybersecurity attacks for its customer base, which represents some of the largest brand-name companies in the world, including BMW, AXA, Zurich, NTT, Sompo Japan and the American Red Cross, as well as numerous other leading global Fortune 500 enterprises. Contrast partners with global organizations such as AWS, Microsoft, IBM, GuidePoint Security, Trace3, Deloitte and Carahsoft, to seamlessly integrate and achieve the highest level of security for customers.
The growing demand for the world’s only platform for code security has landed the company on some of the most prestigious lists, including the Inc. 5000 List of America’s Fastest-Growing Companies and the Deloitte Technology Fast 500 List of fastest-growing companies.
Learn more: https://www.contrastsecurity.com/.
Follow us: Blog | Twitter | LinkedIn | Facebook
Media Contact:
pr@contrastsecurity.com
