How Attackers Trick AI: Lessons from Gandalf’s Creator

The AI Native Dev - from Copilot today to AI Native Software Development tomorrow

Player FM - Internet Radio Done Right

הוסף לפני fifty שבועות

תוכן מסופק על ידי Tessl. כל תוכן הפודקאסטים כולל פרקים, גרפיקה ותיאורי פודקאסטים מועלים ומסופקים ישירות על ידי Tessl או שותף פלטפורמת הפודקאסט שלהם. אם אתה מאמין שמישהו משתמש ביצירה שלך המוגנת בזכויות יוצרים ללא רשותך, אתה יכול לעקוב אחר התהליך המתואר כאן https://he.player.fm/legal.

Crash Course DM

1
The Charcuterie Prose (The Lichual pt 1/2) 1:18:10

לפני 20 weeks1:18:10

הפעל מאוחר יותר

רשימות

לייק

אהבתי

1:18:10

Riddles, troikas, and food references abound! After a forbidden scroll is removed from the Arcane Library from the city of Eltin, a ragtag group of adventurers is dispatched to track it down. Join our party on their mysterious adventure, as Melony Melons tries to make friends, Agent Peaches searches for his next big story, Fromage passes some hot cheese samples to anyone who will listen, and Metzger Abbatoir tries to convince everyone he isn’t his father’s son. Starring: Nathan Zimmerer - Melony Melons Kyle Kane - Agent Peaches Shea Ingram - Metzger Abbatoir AKA Bouchet Chris Arr - Fromage Josh Greenway - The Dungeon Newbie Based on the Unraveled one-shot from Roll & Play Press https://rollandplaypress.com Edited by Josh Greenway Sound Effects provided by Pixabay.com Music Josh Greenway & Mark Canning Clavier Clavier ⁠https://pixabay.com/users/clavier-music-16027823⁠ Kellepics ⁠⁠Https://pixabay.com/users/kellepics-4893063…

לפני שנה 54:35

MP3•בית הפרקים

🔒 How Secure is AI? Gandalf’s Creator Exposes the Risks 🔥
AI security is under attack, and hackers are finding new ways to manipulate AI systems. In this episode, Guy Podjarny sits down with Mateo Rojas-Carulla, co-founder of Lakera and creator of Gandalf, to break down the biggest threats facing AI today—from prompt injections and jailbreaks to data poisoning and agent manipulation.
What You’ll Learn:
- How attackers exploit AI vulnerabilities in real-world applications
- Why AI models struggle to separate instructions from external data
- How Gandalf’s 60M+ attack attempts revealed shocking insights
- What the Dynamic Security Utility Framework (DSEC) means for AI safety
- Why red teaming is critical for preventing AI disasters
Whether you’re a developer, security expert, or just curious about AI risks, this episode is packed with must-know insights on keeping AI safe in an evolving landscape.
💡 Can AI truly be secured? Or will attackers always find a way? Drop your thoughts in the comments! 👇
Watch the episode on YouTube: https://youtu.be/RKCvlJT_r4s

Join the AI Native Dev Community on Discord: https://tessl.co/4ghikjh
Ask us questions: podcast@tessl.io

פרקים

1. How Attackers Trick AI: Lessons from Gandalf’s Creator (00:00:00)

2. Over-Permission in AI Systems (00:02:00)

3. Nebulous AI Functionality (00:07:00)

4. Jailbreaks and Prompt Injections Attacks (00:10:00)

5. Introducing the Dynamic Security Utility Framework (00:18:34)

6. Security in Agentic Systems (00:23:34)

7. Red Teaming for Ai Security Testing (00:28:34)

8. The Future of Agentic Systems (00:35:34)

9. LangChain and Real-World Vulnerabilities (00:42:34)

10. Proactive Security Strategies (00:48:34)

59 פרקים

#Tech #Tessl #AI Native Software Development #Ai Developments #Ai Software Development #AI Native #Ai Assistants #Ai Code Completion