WithSecure Experiments Highlight Language Model Threat

A report published today by WithSecure (formerly known as F-Secure Business) showed how generative pre-trained transformer language models such as GPT-3 can use machine learning to generate text capable of driving phishing and business email compromise (BEC) campaigns at unprecedented levels of scale. While language models are typically trained using a specific corpus of data,..

The post WithSecure Experiments Highlight Language Model Threat appeared first on Security Boulevard.

Article Link: WithSecure Experiments Highlight Language Model Threat - Security Boulevard …

article bec business business email compromise campaigns compromise data driving email email compromise f-secure generative gpt gpt-3 language language models link machine machine learning phishing report scale security security boulevard text threat unprecedented withsecure