AegisAI has released Proteus, the foundational model from the AegisAI Lab that does a full SOC-style investigation of each email before it reaches the inbox. Announced on October 8, 2026 in New York, Proteus investigates every message like a security analyst rather than matching against rules or behavioral patterns, addressing AI-generated attacks that change faster than rule-based systems can update.
AI-generated attacks now change faster than rule-based and behavioral systems can update. While traditional email security relies on historical attack signatures, Proteus acts as an autonomous security analyst auditing the authenticity and contextual integrity of every incoming message. Rather than matching messages against rules or behavioral patterns, Proteus investigates every email that hits your inbox. It checks who sent it, where its links lead, and what it's really asking for. No prior behavior or pattern matching is required.
Every phishing email depends on assertions about who sent it, whether a relationship already exists, where a link goes and what business process it belongs to. Proteus verifies those assertions using signals outside the attacker's control, such as a link's true destination, the correspondence history between sender and recipient, routing and header data, and how the sending infrastructure has behaved elsewhere. Security analysts have long confirmed attacks this way, but investigating by hand doesn't scale beyond a few messages a day. As a result, most security stacks score everything on similarity and investigate only the flagged messages, often after delivery.
Proteus doesn't read an email as raw text. It processes each one as a structured object that combines the message content, headers, sender and recipient history, sanitized link and attachment data, and threat intelligence, with a custom tokenizer built around it.
The launch comes as generative AI makes tailored, convincing phishing cheap to produce at scale, eroding the advantage defenders once had from seeing an attack once and blocking it everywhere else. The team first saw the problem while at Google, where the variety of attacks arriving each day was outgrowing what detection rules and behavioral models could cover.
AegisAI said generative AI has removed the economics that once forced attackers to reuse campaigns. "What was once the purview of nation states is now freely available to the cybercriminal community at large," said Cy Khormaee, Founder and CEO of AegisAI. Over 2025, AI-generated spear phishing rose from under 1% to more than a fifth of the phishing the company tracked. At its current pace, it will make up most attacks by 2028.
These messages also work. A controlled study found that fully automated, AI-written spear phishing achieved a 54% click-through rate, matching human experts and more than four times the 12% rate for generic phishing. AegisAI pointed to a customer incident where attackers used a malicious OAuth grant to take over a Google Workspace account and send bid invitations that passed SPF, DKIM and DMARC. AegisAI flagged the first message 89 minutes before the account-takeover alert.
The evaluation used 3,020 human-verified phishing attacks from a single week of AegisAI's production traffic, none in Proteus training data. Proteus identified more than 99% of attacks, while the leading closed-source model missed 565 and the open-weight model missed 604, around 30 times as many as Proteus. Proteus lead was largest on credential theft and business email compromise, following links to real destinations and checking relationship history.
Speed is critical because email security runs inline, holding each message until a verdict. Proteus was 7.2 times faster than the closed-source model at median and 26 times faster on slowest 5%. An ablation test showed evidence at inference identified 8.4% more phishing. AegisAI calibrates Proteus by examining internal activations, placing 82% of scored messages in usable confidence band with expected calibration error of 0.037.
Since attackers adapt, Proteus is retrained on ongoing basis, must pass adversarial testing across nine attack families, then run side by side with current version on live traffic before replacing it. Proteus is first in planned family of AegisAI Lab models.
About AegisAI
AegisAI is the first AI lab for email security. Founded by a security team from Google, the company builds models that investigate every email before it reaches a person, checking each message's claims against evidence the sender does not control. Its research team includes former leaders of Chrome Enterprise Security, Google Ads Security, GCP AI Platform Security and Google reCAPTCHA/Safe Browsing. Proteus is the first model released by the AegisAI Lab.
