Menlo Security targets real-time AI agent security with MARS platform

Menlo Security targets real-time AI agent security with MARS platform As AI agents gain access to enterprise systems and sensitive data, security teams need greater visibility into their actions. Real-time monitoring and policy enforcement are becoming essential as a part of prompt injection technology. With these challenges in mind, Menlo Security Inc. has sought to respond with Menlo Agent Runtime Security (MARS). In this new environment, many are concerned about the risks associated with AI agents, according to Ramin Farassat (pictured), chief product officer of Menlo Security. “Agents have access to your data. That data can be exfiltrated, and also agents could be quite gullible,” Farassat said. “An agent could be fooled with commands and prompts through prompt poisoning to perform tasks that it’s not designed to be performing.” Farassat spoke with Krista Case at Black Hat USA, during an exclusive broadcast on theCUBE, SiliconANGLE Media’s livestreaming studio. They discussed real-time security controls for AI agents and protecting enterprise data from prompt injection attacks. (* Disclosure below.) On prompt injection technology AI agents are vulnerable to prompt injection because they often fail to distinguish between legitimate data and malicious commands hidden within it. Unlike humans who would question such anomalies, these agents blindly process the poisoned input as valid instructions, according to Farassat. “I don’t believe there will be a prompt injection technology that’s going to be 100% safe and complete, that’s going to stop every possible threat that could be out there,” Farassat said. “What you have to do is you have to use that as one of the tools that you have in your tool bag to deal with various different types of threats.” Menlo Security sets policies and controls the actions that agents can take despite what other commands would be telling them to do, Farassat noted. “We also make sure that we take information, the data that the agent is consuming, and remove sensitive information from that,” Farassat said. “We look for sensitive information in real time, and we can mask that data as well.” Here’s the complete video interview, part of SiliconANGLE’s and theCUBE’s coverage of Black Hat USA: (* Disclosure: Menlo Security Inc. sponsored this segment of theCUBE. Neither Menlo nor other sponsors have editorial control over content on theCUBE or SiliconANGLE.) Photo: SiliconANGLE A message from John Furrier, co-founder of SiliconANGLE: Support our mission to keep content open and free by engaging with theCUBE community. Join theCUBE’s Alumni Trust Network, where technology leaders connect, share intelligence and create opportunities. 15M+ viewers of theCUBE videos, powering conversations across AI, cloud, cybersecurity and more 11.4k+ theCUBE alumni — Connect with more than 11,400 tech and business leaders shaping the future through a unique trusted-based network. Are you AWS customer? Support SiliconANGLE Financially by buying your AWS services from our Marketplace portal page and links. About SiliconANGLE Media SiliconANGLE Media is a recognized leader in digital media innovation, uniting breakthrough technology, strategic insights and real-time audience engagement. As the parent company of SiliconANGLE, theCUBE Network, theCUBE Research, CUBE365, theCUBE AI and theCUBE SuperStudios — with flagship locations in Silicon Valley and the New York Stock Exchange — SiliconANGLE Media operates at the intersection of media, technology and AI. Founded by tech visionaries John Furrier and Dave Vellante, SiliconANGLE Media has built a dynamic ecosystem of industry-leading digital media brands that reach 15+ million elite tech professionals. Our new proprietary theCUBE AI Video Cloud is breaking ground in audience interaction, leveraging theCUBEai.com neural network to help technology companies make data-driven decisions and stay at the forefront of industry conversations.