Google Takes On Scam Messages and Calls on Android with Gemini

Google is using Gemini's cloud and on-device processing to identify complex conversations and suspicious anonymous links in its messaging app.

Google uses Gemina's cloud and local processing capabilities to identify complex conversations and suspicious anonymous links in its messenger.

Become a special member of Arjan Ambassador in order to benefit from and access special facilities and different departments in Arjan Ambassador.

The methods of fraud and deceiving users in the mobile space are changing rapidly. Hackers are no longer just relying on simple robocalls or banal phishing texts, and are using multi-step techniques, impersonation, and even seemingly normal conversations. Based on statistical evaluations, a significant amount of mobile users are deeply concerned about online frauds and threats. To prevent these risks, Google now announced that the Android defense system uses artificial intelligence-based security layers to intercept suspicious messages and calls before trapping the audience.

By introducing a new set of security mechanisms, Google has added a new protection feature called "Enhanced Protection Mode" to Google Messages. In this case, when a conversation is initiated by an anonymous sender, the fraud detection system uses Google's most advanced Gemina AI models in the cloud to evaluate the context and context of complex interactions. This analysis is designed to identify the true intentions of people who hide their sinister intentions behind casual, lengthy or seemingly friendly conversations.

According to a recent survey by Google and YouGov Institute, nearly 40% of smartphone users are very concerned about new fraud methods such as artificial intelligence voice simulation and number spoofing. According to Google, the fraud detection tools based on artificial intelligence in the call and messaging application of this company currently identify and block more than 5 million suspicious calls and text messages per month.

To fully protect people's privacy, Google says Gemini-based processing is done in an encrypted and dedicated environment called Private AI Compute. In this secure mechanism, information is evaluated in a separate space and no third party, not even Google itself, will have access to the exchanged content. This cloud analysis enhances the power of the device's internal detection system, allowing the most sophisticated attacks and new fraud patterns to be quickly thwarted.

In addition to text monitoring, link health checks have also been improved. Because hackers are constantly creating new domains and websites that have not yet been blacklisted, Gemina Nano's model scans the web for real-time web cues and signals locally on the device to assess the credibility of unfamiliar links before the user touches them. Also, redesigned warnings are embedded to give clearer warnings when receiving links from unknown numbers and prevent accidental clicks.

In addition, the ability to detect suspicious messages in the notification section, which was previously only for the Pixel series, will be available to hundreds of millions of other users in different brands by the end of this year in cooperation with mobile phone manufacturers, so that the user will be aware of the suspicious nature of the message before opening the messengers.

Another part of the new defense layers is dedicated to dealing with social engineering methods. A common trick by fraudsters is to trick users into diverting or misdirecting calls using manual MMI codes so that they can steal one-time passwords (OTPs). Android now prevents apps from secretly activating the divert in the background, and if the user is tricked into dialing these codes manually, it will warn them before they apply. Also, the ability to automatically hide passwords and bank card information during screen sharing has now been extended to the Chrome browser and Android WebView to avoid revealing sensitive information during video calls.

Google's most important achievement in voice calls is the instant countering of impersonation of banks through fake numbers. Android, in direct cooperation with the official applications of financial institutions, inquires the validity of the incoming call at the moment, and if the call is not confirmed by the bank, the call is immediately cut off and the user is warned; A mechanism that has been able to block more than 3 million deceptive calls only in the initial tests. Google has also emphasized, citing the technical evaluations of the Leviathan Security Group research company, that the native and default capabilities of Android in the field of dealing with fake calls and warning threats provide a more effective performance than the iOS operating system.

My professional career in the world of technology goes back almost 10 years; The path that started with hardware, continued with software, and now continues as a technology reporter in Sefir Arjan. I am Javad and more than three decades have passed and in addition to the world of technology, I love movies and cinema, classic rock music and Real Madrid.

How good that Google can increase the security of Android phones against unknown and malicious links. Even now, from versions 14 and later, Google Messenger checks this issue quickly after sending each message, and if it sees a suspicious link, it enters it into the Spam folder and even blocks the sent number.