top of page

Reliable and Trustworthy AI: Challenges in the Era of LLMs and Agentic AI

Ensuring Reliability and Trustworthiness of AI systems is crucial in the era of LLMs and, of course, particularly in the realm of Agentic AI. This talk explores strategies to mitigate risks in AI-powered systems by enhancing transparency, fostering integrity, and applying watermarking for better traceability.

Time & Place

March 31, 2025

16:00 - 18:00

The Ritz-Carlton Berlin

Salon Bellevue

Classroom Seating

Max. Capacity: 64 Seats

Meet Your Intructors

Prof. Dr. Gerhard Wunder

Professor of Cybersecurity and Artificial Intelligence, Freie Universität Berlin

Prof. Dr.-Ing. habil. Gerhard Wunder is a Professor of Cybersecurity and Artificial Intelligence at Freie Universität Berlin, leading the Cybersecurity and AI (C-AI) Group.

Supported by Bundesdruckerei GmbH, his group focuses on AI with cybersecurity and cybersecurity through AI, hosting the Center for Trustworthy AI at the university. Prof. Wunder's research encompasses generative AI, resilient networks, privacy-preserving synthetic data, explainability and fairness in AI, quantum crypto analysis, AI engines for anomaly detection, cybersecurity architectures in IoT, AI-assisted device biometrics, and low-resource federated learning with blockchains.

His work bridges the gap between advanced AI technologies and practical cybersecurity solutions, driving progress in creating secure and intelligent systems for real-world applications. Prof. Wunder is dedicated to promoting innovation in AI and cybersecurity, making significant contributions to both academic research and industry practices.

What To Expect

Who Is This For?

  • AI Governance & Compliance Leaders

  • Enterprise AI & Risk Management Teams

  • Machine Learning & AI Engineers

  • Ethics & Policy Experts in AI

  • Investors & Innovators in AI Security

Pre-Requisites

  • No specific technical skills required

  • Bring Your Own Laptop

What You'll Learn & Do?

  • Strategies to enhance AI reliability & trustworthiness

  • Risk mitigation techniques for AI-powered systems

  • How transparency, integrity, and watermarking improve AI traceability

Agenda & Activities

Agenda for this session:

  • Getting Settled - 5 mins

  • Information Session - 40 mins

  • Break - 5 min

  • Individual / Group Exercise - 20 min

  • Q&A/Discussion - 20 min

  • Reflection - 5 min


Prerequisits:

  • Bring Your Own Laptop

Registration

In order to register to our workshops you must purchase a Platinum Pass. With the Pass you are eligible to select up to 4 workshops. If you are interested in attending only one workshop you may purchase the Gold Plus Pass.

WhatsApp button (66 x 66 px).png
bottom of page