AI - About Data Ingestion and Prompt Poisoning [in-person]

![AI - About Data Ingestion and Prompt Poisoning [in-person]](https://secure.meetupstatic.com/photos/event/f/4/5/600_526623909.webp?w=750)
Details
Our lineup is complete, it is going to be all about how to enable scalable data integration for AI ingestion and how to actually turn an LLM to the dark side with Prompt Injection.
Please do not overlook the venue: this time we are hosted by our friends at Certible.
What to expect:
🗣️ Two or Three speakers
👥 Meet old and new friends from the community
🍕 Free food
🎉 Open-end and free drinks afterwards
✔️ Just RSVP!
Agenda:
- 17:30 - Doors open
- 18:00 - Welcome
- 18:10 - first talk
- 18:55 - Break
- 19:05 - second talk
- 19:50 - 🎉 Open-end
👂 Talks:
🗣️ Keno Dreßel
Prompt Injection, Poisoning & More: The Dark Side of LLMs
🗣️ Philipp Roth
Data Integration Patterns to successfully drive AI Ingestion
(That Even Work at Large-Scaled Enterprises)
🧑💻 Speakers:
Keno Dreßel, leading the Data & AI initiatives at SQUER. He has extensive experience in full-stack development and integrating AI and machine learning solutions. His talk provides an overview of the key security risks in LLM-based systems and applications. It covers threats like Prompt Injection, Data Poisoning, Model Leakage, and other vulnerabilities, explaining their impact and showing examples. Practical strategies for securing LLM implementations will also be discussed.
Philipp Roth, is a technical architect and freelance consultant specializing in data and system integration for large-scale enterprises. He focuses on event-driven architectures, data streaming, and scalable integration patterns to help organizations make the most of their data. His talk will be about getting data from different systems into a usable, reliable pipeline, which is a challenge—especially at scale. This talk explores data integration patterns that help streamline ingestion, whether for analytics, machine learning, or operational systems. We’ll look at event-driven architectures, change data capture, and real-time streaming, tackling key challenges like latency, freshness, and scalability.
Location:
Certible @ Löwelstraße 20, 1010 Vienna
------------
Can't find what you like? Got something to say? 📢
Send us your thoughts for the next event here!
Whether you’re a seasoned speaker or stepping onto the stage for the first time, we’d love to have you share your insights at one of our upcoming events. Interested in giving a talk? Let us know!
Our formats:
• Full talks (~30 to 45 min.)
• Short talks (~15 min.)

AI - About Data Ingestion and Prompt Poisoning [in-person]