| ★ |  PromptShield™ Vs LLMs Exploiting NPM Packages | | 14 | Estados Unidos | |
| 20 |  AI Privilege Escalation: Agentic Identity & Prompt Injection Risks | IBM Technology @ibmtechnology | — | Estados Unidos | 86 |
| 17 |  Firewall Demo of Red Team vs Blue Team: Hacking Finance Apps with AI Chatbots | | 2.8M | Reino Unido | 86 |
| 11 |  Prompt Injection in AI | Data Engineering @dataengineeringtamil | 12.6K | India | 87 |
| 13 |  LiteLLM Compromised | Abhishek.Veeramalla @abhishekveeramalla | 10.6K | India | 87 |
| 12 |  legally hack AI in 13 minutes | | 10.0K | — | 87 |
| 8 |  Prompt engineering with security 🛡️🛡️🛡️ | | 8.5K | India | 87 |
| 18 |  How to Pentest LLMs Like a Security Researcher Cybersecurity | | 4.2K | India | 86 |
| 19 |  Promptware, cloud security trends for 2026, and what the Xbox One hack means for cybersecurity | IBM Technology @ibmtechnology | 2.3K | Estados Unidos | 86 |
| 14 |  AI Browsers Are Stealing Your Data (Prompt Injection Explained) | | 1.5K | Estados Unidos | 87 |
| 10 |  Hacking AI without code | What's AI by Louis-François Bouchard @whatsai | 1.0K | Canadá | 87 |
| 6 |  Shadow AI: The Silent Cybersecurity Threat Businesses Can't Ignore | | 383 | Estados Unidos | 88 |
| 3 |  Adversarial Image Attacks Explained | | 272 | Estados Unidos | 91 |
| 4 |  AI Security Frameworks: Must-Know Challenges & Solutions For 2025 | | 220 | Estados Unidos | 89 |
| 5 |  AI Ethics That Work: Privacy, Fairness & Security | | 201 | Estados Unidos | 89 |
| 2 |  PromptShield™ Vs Google Calendar Invitation Attacks | | 44 | Estados Unidos | 92 |
| 7 |  Building AI-Powered Security for AI Chatbots | | 33 | — | 88 |
| 1 |  PromptShield™ Vs Claude File Creation Attacks | | 25 | Estados Unidos | 95 |
| 9 |  How Defiance XDR™ Secures Small Businesses | | 21 | Estados Unidos | 87 |
| 15 |  The Differences Between XDR And Other Security Solutions | | 15 | Estados Unidos | 86 |
| 16 |  Securing ChatGPT & LLMs in AWS: Your Ultimate Guide | CyberShield Simplified @cybershieldsimplified | 5 | Estados Unidos | 86 |