Researchers used an open-source tool to generate malicious prompts that evade content filters in ChatGPT, Bard, and Bing Chat.
Source: Motherboard
This AI Chatbot is Trained to Jailbreak Other Chatbots
- U.K., U.S. and Canadian Cyber Authorities Warn of Pro-Russia Hacktivist Attacks on Operational Technology Systems
- Top 5 Global Cyber Security Trends of 2023, According to Google Report
- Stronger cybersecurity aimed by Menlo Security, Google Cloud collaboration
- How Are APAC Tech Salaries Faring in 2024?
- Apple earnings: About that iPhone ‘slump’ in China