| ★ | The Hilariously Easy AI Jailbreak (No Coding Required) | | 108.3K | Estados Unidos | |
| 6 | I Jailbroke an AI to Do Anything I Say | | — | — | 88 |
| 7 | GROK AI Uncensored & Unfiltered with Jailbreak Prompt! | | — | Estados Unidos | 88 |
| 15 | Teachers HATE This! How to Bypass AI Detection in 2025 | Milktea Emma @milktea-emma | — | Estados Unidos | 88 |
| 17 | Data Poisoning: The Fatal Flaw in Mass Surveillance | | 1.4M | Estados Unidos | 88 |
| 5 | Google Big Sleep: The End of Human Hackers? | | 932.3K | Reino Unido | 89 |
| 20 | Warning and demo: Hackers can use AI to create malware | | 796.3K | Reino Unido | 88 |
| 13 | Stop Using Restricted AI. Build This Instead. | | 73.3K | — | 88 |
| 1 | What Is AI Jailbreaking? | AI Jailbreaking Explained For Beginners | #Shorts | #Simplilearn | Simplilearn @simplilearnofficial | 55.5K | Estados Unidos | 90 |
| 3 | I Tested an AI Hacker | | 17.6K | — | 89 |
| 2 | legally hack AI in 13 minutes | | 10.0K | — | 89 |
| 19 | HACKERS Are Using This AI Tool | | 9.2K | — | 88 |
| 14 | I Left an AI Hacker Alone for 1 Hour and This Happened… | Cybersecurity Lab Idea | Meera Tamboli @meeratamboli | 4.5K | Reino Unido | 88 |
| 16 | AI Jailbreaks That Made Me Go WTF | The Cyber Mentor @tcmsecurityacademy | 2.3K | Estados Unidos | 88 |
| 9 | AI Browsers Are Stealing Your Data (Prompt Injection Explained) | | 1.5K | Estados Unidos | 88 |
| 11 | Grok Jailbreak Secrets EXPOSED | AllAboutAI @allaboutai.official | 1.4K | Estados Unidos | 88 |
| 18 | Hacking AI without code | What's AI by Louis-François Bouchard @whatsai | 1.0K | Canadá | 88 |
| 12 | Quantum Machine Learning Security: Protecting Your Models From Future Algorithmic Attacks | NobleX Infinity Labs®️ @noblexinfinitylabs | 90 | India | 88 |
| 10 | The Data Behind Why Most Breaches Still Start with People (ep. 7) | SecurityMetrics, Inc. @securitymetrics | 63 | Estados Unidos | 88 |
| 8 | AI Security Explained in 10 Minutes | The Myths, Risks & Future of Cyber Defense | | 51 | Estados Unidos | 88 |
| 4 | Building AI-Powered Security for AI Chatbots | | 33 | — | 89 |