WithSecure Experiments Highlight Language Model Threat

From securityboulevard.com

WithSecure language Expel BEC Delivering Email Post-Data Breach

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, WithSecure researchers were able to expose these models to additional content that could be used to prompt a specific outcome. For example, an article that made false claims could be used to generate an entire stream of similar harmful or misleading content.

Read more…