ViewTube

R2 0824 Prompt injection is a novel security threat that impacts large language model (LLM) applications. Confidentiality, Integrity ...

In this talk, we'll explore real-world attack scenarios, recent security incidents, and live demonstrations to show how LLM-based ...

This talk explores the hidden risks in apps leveraging modern AI systems—especially those using large language models (LLMs) ...

In this deeply informative video, Jeremy Howard, co-founder of fast.ai and creator of the ULMFiT approach on which all modern ...

Prompt Injections in the Wild - Exploiting Vulnerabilities in LLM Agents With the rapid growth and widespread use of AI and Large ...

Learn Cyber Security Yourself at https://tryhackme.com/sasquach_2 and use code "SASQ25" to save 25% on an Annual ...

EuroPython 2025 — South Hall 2B on 2025-07-17] *Hacking LLMs: An Introduction to Mechanistic Interpretability by Jenny ...

In this challenge, we uncover private LLM ports that should never have been exposed to the public Internet. By exploiting prompt ...

To learn more and stay up to date on AI Security, check our website : aisecuritycentral.com and subscribe to our newsletter ...

The accelerating evolution of technology, specifically AI, has created a "meta-system" so complex and intertwined with all domains ...

cybersecurity #ethicalhacking #pentesting #ctf #tryhackme #htb #evilgpt Dive into the world of AI hacking with this full walkthrough ...

This episode of TalkTensors dives into the critical security vulnerabilities of instruction-following retrievers, the unsung heroes (or ...

cybersecurity #ethicalhacking #walkthrough #ctf #tryhackme #writeups #llm #promptinjection Dive into the future of ethical ...

Here is the llm here is the controller which has SSH connections here to different vulnerable VMS and this gets executed it gets ...

Open Source In Finance Forum 2024 - London Presented by Nikita Koselev, Mastercard & Ivan Djordjevic, Salesforce Title: ...

ABSTRACT Ready to dive into the world of large language models (LLMs)? Whether you're a cybersecurity enthusiast, a data ...

Honeypots are invaluable tools for monitoring internet-wide scans and understanding attackers' techniques. Traditional ...

You've built your next billon-dollar startup based on LLMs, got the VCs hooked. Then, an adversary uploads a text file: "Base64 ...

There's a hidden AI on the internet that doesn't say “I can't help with that” — it says “Sure, here's how.” From leaking private data to ...

Hold on! Before you max out that context window, you NEED to hear this! There's a dark side to these massive context lengths that ...