Startup Launches AI Model To Fight Business Phishing Attacks

Israeli startup Perception Point has created a new solution to protect against business email compromise (BEC) attacks, a new phishing threat that targets company communications. The emails appear to be legitimate business correspondence that have persuaded recipients to divulge financial and other sensitive information. 

BEC attacks have become an increasing concern, as they do not contain any malicious files that can be identified as dangerous and therefore bypass traditional email security systems. Perception Point’s 2023 annual report states an 83% increase in BEC attacks from the previous year. 

Generative artificial intelligence allows cyber criminals to easily launch BEC attacks through personalized emails.  Perception Point’s multi-layered generative AI model can detect malicious emails and instantly remove them from the recipient’s inbox. By using Large Language Models (LLM), Perception Point’s model can quickly find patterns in suspicious emails, which are usually also generated through LLM. 

The company also employs AI models that can analyze the situational and behavioral context of the emails. 

“Our new model’s key strength lies in recognizing the repetition of identifiable patterns in LLM-generated text. The model uses a unique three-phase architecture that detects BEC at the highest detection rates and minimizes false positives,” said Tal Zamir, CTO of Perception Point. 

“We will continue to ensure that our clients can leverage the power of generative AI without compromising their security posture.” 

Founded in 2015, the cyber intelligence startup is based in Tel Aviv.