Part 7/9:
Robust Intelligence has provided evidence of successful jailbreak attempts on models like ChatGPT, revealing instances where malicious actors might craft phishing messages or stay hidden on government networks. These growing concerns have prompted researchers, including those from the University of Pennsylvania, to devise more efficient methods of uncovering potential vulnerabilities in AI systems.
Brendan Dolan-Gavitt, an expert at NYU specializing in computer security and machine learning, emphasizes that relying solely on human-led fine-tuning is insufficient to secure these models. He advocates for additional protective measures to combat the nature of these emerging threats.