התחל במצב לא מקוון עם האפליקציה Player FM !
How Attackers Trick AI: Lessons from Gandalf’s Creator
Manage episode 472050790 series 3585084
🔒 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)
57 פרקים
How Attackers Trick AI: Lessons from Gandalf’s Creator
The AI Native Dev - from Copilot today to AI Native Software Development tomorrow
Manage episode 472050790 series 3585084
🔒 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)
57 פרקים
כל הפרקים
×ברוכים הבאים אל Player FM!
Player FM סורק את האינטרנט עבור פודקאסטים באיכות גבוהה בשבילכם כדי שתהנו מהם כרגע. זה יישום הפודקאסט הטוב ביותר והוא עובד על אנדרואיד, iPhone ואינטרנט. הירשמו לסנכרון מנויים במכשירים שונים.