Mastodawn

Brian Vermeer May 29, 2025

Prompt injection is quickly becoming one of the key security challenges in the world of AI and LLMs.

We just published a new article that explores prompt injection, the different types of attacks, and why it’s such a complex issue to solve.

https://t.co/IxFxCiRAiU

Understanding Prompt Injection: 8 Common Techniques, Challenges, and Risks | Snyk

A prompt injection attack is a GenAI security threat where an attacker deliberately crafts and inputs deceptive text into a large language model (LLM) to manipulate its outputs.

Snyk

Brian Vermeer May 16, 2025

Our talk on Securing LLM-powered applications from
@DevoxxFR is live. In this talk, @lizeraes
and I will break LLMs and give you pointers on how to solve this.
https://t.co/lAI6SBJkDl

Securing LLM-Powered Applications: Overcoming Security and Privacy Challenges

Présentation par : Brian Vermeer (Netherlands / Snyk), Lize Raes (Switzerland / Naboo.ai)📕 Resumé : LLMs accessing the database and intelligent agents that ...

YouTube

Brian Vermeer May 7, 2025

Building with AI? Don’t skip safety. This article explains how LLM guardrails can protect your applications and users: https://t.co/BRNRAcGeJf

Ensuring Safe and Reliable AI Interactions with LLM Guardrails | Snyk

Explore LLM guardrails, why they matter, and how you can effectively implement them to ensure safe and trustworthy AI interactions.

Snyk

Brian Vermeer Apr 25, 2025

RAG is great to enhance and improve your AI responses, but it is also a new attack vector. So what are the security implications of using RAG?
https://t.co/T1tSNgnxBB

What is RAG, and how to secure it | Snyk

Learn how Retrieval-Augmented Generation improves LLMs with your data. Understand critical RAG security risks & discover best practices to protect your AI.

Snyk

Brian Vermeer Apr 20, 2025

A small snapshot before our LLM security talk at @DevoxxFR this week. The room ended up being packed and the talk was rated in the top 2 best talks 😱. Merci Devoxx France for the great experience et a bientot. https://t.co/xbLjBTuqM5

Brian Vermeer (@BrianVerm) on X

X (formerly Twitter)

Brian Vermeer Apr 9, 2025

Spoke at the first-ever @VoxxedAmsterdam last week. Great crowd, great energy.

My talk covered real-world security issues in LLM-powered apps, including actual hacks and practical solutions.
https://t.co/ORh3DjiWPM

Congrats to the crew on a successful inaugural edition.

Breaching LLM Powered Applications: Overcoming Security and Privacy Challenges by Brian Vermeer

YouTube

Brian Vermeer Apr 4, 2025

From our tram to yours “Voxxed days Amsterdam” edition
@MaritvanDijk77 @alina_yurenko @ammbra1508 @JohanHutting @BalaRawool
@VoxxedAmsterdam https://t.co/ZO3cWhfz5y

Brian Vermeer (@BrianVerm) on X

From our tram to yours “Voxxed days Amsterdam” edition @MaritvanDijk77 @alina_yurenko @ammbra1508 @JohanHutting @BalaRawool @VoxxedAmsterdam

X (formerly Twitter)

Brian Vermeer Mar 20, 2025

GraalVM session by @alina_yurenko at @JavaOne. And obviously #eatingwhileothersareworking https://t.co/Bk0ktdSyIY

Brian Vermeer (@BrianVerm) on X

GraalVM session by @alina_yurenko at @JavaOne. And obviously #eatingwhileothersareworking

X (formerly Twitter)

Brian Vermeer Mar 19, 2025

#JavaOne 2025 https://t.co/WNysPIIFoP

Brian Vermeer (@BrianVerm) on X

#JavaOne 2025

X (formerly Twitter)

Brian Vermeer Mar 9, 2025

I’m super excited to speak at ⁦@JavaOne⁩ about GenAI coding assistants and their security implications. If you’re attending JavaOne, let’s connect and have a chat! https://t.co/PTIiaXlk6u

Brian Vermeer (@BrianVerm) on X

I’m super excited to speak at ⁦@JavaOne⁩ about GenAI coding assistants and their security implications. If you’re attending JavaOne, let’s connect and have a chat!

X (formerly Twitter)