WormGPT Unleashed: A Menace in the Hands of Cybercriminals
With generative artificial intelligence (AI) on the rise, it has unfortunately become a tool of choice for malicious actors, creating a fast track to cybercrime.
A novel generative AI cybercrime tool, dubbed WormGPT, has emerged in underground forums, offering adversaries a potent weapon for launching sophisticated phishing and business email compromise (BEC) attacks.
Security researcher Daniel Kelley warns, "This blackhat alternative to GPT models is tailored for malicious activities, automating the creation of highly convincing fake emails that are personalized to their targets, thereby amplifying the attack's success rate."
The software's creator boasts that it is "the arch-nemesis of the well-known ChatGPT," empowering users to engage in illicit activities.
In the wrong hands, WormGPT becomes a formidable weapon, especially as OpenAI ChatGPT and Google Bard are proactively addressing the abuse of large language models (LLMs) to create deceptive phishing emails and malicious code.
Compounding the issue, threat actors are actively promoting "jailbreaks" for ChatGPT, orchestrating customized prompts and inputs to exploit the tool's vulnerabilities and induce outputs that may expose sensitive information, generate inappropriate content, and even execute malicious code.
Source: https://thehackernews.com/2023/07/wormgpt-new-ai-tool-allows.html