LLMjacking Exposed: How Attackers Hijack Agentic AI Models | NHIcon 2025 скачать в хорошем качестве

LLMjacking Exposed: How Attackers Hijack Agentic AI Models | NHIcon 2025

AI misuse ranks high on cybersecurity forecasts for 2025, and for good reason. This session explores LLMjacking, a newly identified threat by the Sysdig Threat Research Team, showcasing how attackers exploit large language models to bolster their malicious activities. After we discuss the details of this real-world threat, attendees will witness a live demonstration of prompt injection, where an LLM is manipulated into executing malicious code. About Aembit Aembit is the non-human identity and access management platform that secures access between workloads across clouds, SaaS, and data centers. With Aembit’s identity control plane, DevSecOps can fully automate secretless, policy-based, and Zero Trust workload access with MFA-strength capabilities. 📔 Get more Aembit! Website: https://www.aembit.io/ LinkedIn:   / aembit