Will's Blog: Researchers: DeepSeek's R1 failed to detect or block any of the 50 malicious prompts that were tested; Adversa: R1 is vulnerable to many jailbreaking tactics (Wired)

31 January 2025

Researchers: DeepSeek's R1 failed to detect or block any of the 50 malicious prompts that were tested; Adversa: R1 is vulnerable to many jailbreaking tactics (Wired)

Wired:
Researchers: DeepSeek's R1 failed to detect or block any of the 50 malicious prompts that were tested; Adversa: R1 is vulnerable to many jailbreaking tactics — Security researchers tested 50 well-known jailbreaks against DeepSeek's popular new AI chatbot. It didn't stop a single one.

Posted from: this blog via Microsoft Power Automate.