Simonas Černiauskas
Dr.-Ing. Simonas Černiauskas is the founder and CTO of tisix.io, specializing in developing practical LLM solutions for media and publishers. With a doctorate from RWTH Aachen and experience as a principal researcher at Research Center Jülich, he combines deep technical expertise with hands-on implementation experience. His work focuses on multi-modal content generation and media processing. Drawing from his background in mechanical engineering, quality assurance and machine learning engineering, Simonas develops scalable AI solutions while maintaining a strong focus on quality assurance and risk management. He regularly shares insights through speaking engagements and technical publications, helping organizations navigate the complexities of AI implementation with practical, business-focused approaches.
Session
Before you ship an AI agent to production, you need to understand how it can be broken. Jailbreaking and prompt injection attacks are not edge cases—they are an inevitable consequence of deploying real-world, action-taking AI systems.
This talk is a practical primer on the most common ways agents fail under adversarial pressure. We’ll break down how jailbreaking and prompt injection attacks actually work, including techniques such as excessive agency, prompt leakage, and weaknesses in vector search and embeddings. We’ll examine why popular AI guardrails consistently fail in practice, and offer little more than a false sense of protection.
We’ll also address a common misconception: the absence of major AI security incidents does not mean systems are safe. Instead, it reflects limited deployment, constrained agency, and cautious rollout. As organizations adopt browser agents, autonomous tools, and systems that can take real-world actions, these vulnerabilities quickly become critical attack surfaces.
This talk focuses on what organizations should do instead: applying proven security principles—least privilege, isolation, monitoring, and abuse modeling—adapted to the unique properties of AI systems. Attendees will leave with a clear understanding of the real risks, why they matter today, and the concrete steps to take before shipping an AI agent into production.