DEMASQ: Unmasking the ChatGPT Wordsmith

Kavita Kumari

Network and Distributed System Security (NDSS) Symposium 2024 · Day 3 · LLM Security

The proliferation of Large Language Models (LLMs) like ChatGPT has ushered in a new era of content generation, but with it, a critical challenge: the inability to reliably distinguish between human-generated and AI-generated text. This talk introduces **DEMASQ**, a novel ChatGPT detector designed to address this pressing issue. Given by Kavita Kumari, this research tackles the alarming rise in misinformation, plagiarism, academic dishonesty, and various fraudulent activities facilitated by AI-generated content. Existing detection methods often fall short, lacking precision, being domain-specific, and proving inadequate against sophisticated models like ChatGPT.