Google’s Pixel Phone App Introduces Real-Time AI Fraud Detection in Beta

執筆者
Sunny Yadav
Sunny Yadav
Nov 24, 2024
2 minute read
Two young women, one African American and one Asian, happily pose for a selfie while enjoying a picnic in a park.
eWeek のコンテンツおよび製品のおすすめは、編集上の独立性を保っています。パートナーへのリンクをクリックすると、当社が報酬を得る場合があります。 詳細を見る

Google has unveiled a new feature for its Pixel devices that uses AI to identify and alert users to potential scam calls in real time. Currently in beta, this AI fraud detection feature is available in the Phone by Google app for Pixel 6 and newer devices, with Pixel 9 users leveraging the cutting-edge Gemini Nano for detection.

How Real-Time AI Fraud Detection Works

The new feature monitors calls from unknown numbers in real time, flagging suspicious activity without storing or sharing sensitive data. It operates automatically in the background, ensuring existing contacts remain unaffected.

  • If a scam is suspected, users are alerted with a vibration, sound, and a warning message, “Suspicious activity detected.”
  • An “End call” button allows them to immediately terminate the conversation, while a “Not a scam” option can be used to mark legitimate calls.

The feature relies on on-device processing, ensuring all data remains private and secure. The Fraud Detection feature is disabled by default. You can enable it manually in the Phone app under the Assistive category, which also houses features like Call Screen and Hold for Me. Once activated, it seamlessly integrates with the app to provide real-time scam detection.

Pixel 9 devices use Google’s advanced Gemini Nano technology for detection, while Pixel 6 and newer models leverage other machine learning models. Google has emphasized that no audio recordings or transcripts are stored, with all processing conducted locally on the device. This privacy-focused approach sets the feature apart from traditional call-screening tools, offering robust protection while respecting user data.

Limitations and Availability

The AI-based fraud detection feature is in beta and available only for U.S. users running version 154 of the Phone by Google app. It supports English language calls and is not guaranteed to detect every scam due to fraudsters’ ever-evolving tactics.

Despite these limitations, the tool represents a step forward in combating increasingly sophisticated scam calls. However, some have criticized its limited availability, urging Google to expand access to more regions and languages.

A Step Toward Safer Calls

Google’s latest effort in fraud detection with AI analytics demonstrates the potential for real-time scam prevention on smartphones. As scams grow more complex, tools like this offer users greater control over their security.

While still in its early stages, this innovation underscores Google’s commitment to protecting users against fraud and highlights the growing role of AI fraud detection software in safeguarding everyday communications.

Sunny Yadav

Sunny is a content writer for eSecurity Planet (eSP) with a bachelor’s degree in technology and experience writing for leading cybersecurity brands like Panda Security, Upwind, and Vanta. At eSP, he covers the latest news on cyberattacks, cryptography, data protection, and emerging threats and vulnerabilities. He also explores security policies, governance, and endpoint and mobile security. Sunny enjoys hands-on testing, rigorously evaluating tools to assess their capabilities and real-world performance. He also has extensive experience working with AI tools like ChatGPT and Gemini, experimenting with their applications in cybersecurity, content creation, and research.

eWeek Logo

eWeek has the latest technology news and analysis, buying guides, and product reviews for IT professionals and technology buyers. The site's focus is on innovative solutions and covering in-depth technical content. eWeek stays on the cutting edge of technology news and IT trends through interviews and expert analysis. Gain insight from top innovators and thought leaders in the fields of IT, business, enterprise software, startups, and more.

TechnologyAdvice が所有・運営しています。 © 2026 TechnologyAdvice. 無断転載を禁じます

広告主に関する開示:このサイトに掲載されている製品の一部は、TechnologyAdvice が報酬を受け取っている企業のものです。この報酬は、製品がこのサイトのどこにどのように表示されるか(表示される順序など)に影響する場合があります。TechnologyAdvice は、市場で入手可能なすべての企業やすべての種類の製品を掲載しているわけではありません。