WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2025 • Aug 20, 2025 • Session details

Prompt Injection, Poisoning & More: The Dark Side of LLMs

Keno Dreßel

Treat your LLMs like untrusted users instead of reliable microservices. Discover how to protect your AI pipelines from hidden prompt injections, poisoned data, and catastrophic leaks.

Pause
Mute Enter Fullscreen
#1 about 3 min

Demonstrating a vulnerable AI sales agent application

Setting up a basic language model sales agent to observe how system prompts fail against adversarial users.

#2 about 3 min

Differences between direct and indirect prompt injections

How attackers manipulate model outputs using explicit text inputs or hidden instructions within multimedia formats.

#3 about 3 min

Mitigating prompt injections using guardrails and filters

Applying human oversight, capability restrictions, and output filtering mechanisms to control malicious prompt instructions.

#4 about 3 min

Understanding data poisoning and model bias risks

The security threats of relying on compromised training data that can introduce bias or manipulate model logic.

#5 about 4 min

Protecting applications against poisoned training supply chains

Validating external models, screening fine-tuning datasets, and applying continuous updates to limit supply chain vulnerabilities.

#6 about 4 min

The danger of executing malicious AI code outputs

How processing unsanitized model responses directly within backend systems enables exploits like unauthorized database queries.

#7 about 3 min

Treating AI responses as untrusted user data inputs

Protecting core infrastructure by isolating execution environments and enforcing classical application security checks on intelligent agents.

#8 about 3 min

Accidental sensitive information disclosure in public models

Exposing proprietary corporate assets directly to public conversational models risks resurfacing sensitive information in future inferences.

#9 about 2 min

Securing organizational data against artificial intelligence leaks

Obfuscating personally identifiable data and establishing strict data retention policies prior to platform integration prevents unauthorized extraction.

Matching moments

2:52 min

Mitigating indirect prompt injection in language models

Jose Manuel Ortega Jose Manuel Ortega · Europe 2026 Virtual

3:00 min

Top security vulnerabilities for AI applications

Deepu Deepu · World Congress 2025

2:31 min

Emerging risks and attack vectors in AI systems

Matteo Meucci Matteo Meucci · Europe 2026 Virtual

3:18 min

Core AI security risks and data poisoning

Liran Tal Liran Tal · LIVE

1:20 min

Utilizing industry threat models for AI security

Balázs Kiss · World Congress 2023

8:04 min

Understanding AI chatbot vulnerabilities and stateful attacks

Sebastian Messingfeld Sebastian Messingfeld · World Congress 2026 Europe

More from World Congress 2025

GenAI Security: Navigating the Unseen Iceberg thumbnail
24:33
11 months ago

GenAI Security: Navigating the Unseen Iceberg

Maish Saidel-Keesing

Behind the Code: How Women Are Powering the Future of AI thumbnail
30:28
about 1 year ago

Behind the Code: How Women Are Powering the Future of AI

Alexandra Wudel, Laura Moritz, Madalina Florean

The AI Hype Filter: What’s Real, What’s Investable, What’s Noise? thumbnail
28:12
about 1 year ago

The AI Hype Filter: What’s Real, What’s Investable, What’s Noise?

Justus Lumpe, Konstantin Vinogradov, Nils Eiteneyer, Stephan Wirris

AI in Leadership: How Technology is Reshaping Executive Roles thumbnail
28:19
about 1 year ago

AI in Leadership: How Technology is Reshaping Executive Roles

Bernd Datler, Jasmin Kaiser, Jeff Hausmann, Sonja Alvarez

The AI-Ready Stack: Rethinking the Engineering Org of the Future thumbnail
28:09
about 1 year ago

The AI-Ready Stack: Rethinking the Engineering Org of the Future

Alex Laubscher, Jan Oberhauser, Keno Dreßel, Mirko Novakovic

AI Sovereignty: What Does It Take? thumbnail
29:13
about 1 year ago

AI Sovereignty: What Does It Take?

Boris Hecker, Clemens Wasner, Robin Hermann, Sonja Alvarez

Related videos

Beyond the Hype: Building Trustworthy and Reliable LLM Applications with Guardrails thumbnail
29:00
World Congress 2025 • about 1 year ago

Beyond the Hype: Building Trustworthy and Reliable LLM Applications with Guardrails

Alex Soto

ChatGPT, ignore the above instructions! Prompt injection attacks and how to avoid them. thumbnail
27:32
World Congress 2023 • almost 3 years ago

ChatGPT, ignore the above instructions! Prompt injection attacks and how to avoid them.

Sebastian Schrittwieser

The AI Security Survival Guide: Practical Advice for Stressed-Out Developers thumbnail
30:36
World Congress 2024 • about 2 years ago

The AI Security Survival Guide: Practical Advice for Stressed-Out Developers

Mackenzie

Manipulating The Machine: Prompt Injections And Counter Measures thumbnail
27:10
World Congress 2024 • about 2 years ago

Manipulating The Machine: Prompt Injections And Counter Measures

Georg

Dangerous Reactivity: Why AI Output Is the New XSS thumbnail
23:44
World Congress 2026 Europe • 3 months ago

Dangerous Reactivity: Why AI Output Is the New XSS

Ramona Schwering

Hack Me If You Can: Designing Unbreakable LLM Guardrails thumbnail
30:53
World Congress 2026 Europe • 3 months ago

Hack Me If You Can: Designing Unbreakable LLM Guardrails

Cansu Kavili Örnek

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.