Posted: December 5, 2023 10:18 AM Updated: December 5, 2023 10:18 AM
Correction and fact check date: December 5, 2023, 10:18 AM
briefly
Google today unveiled an AI-based spam detection system designed to identify “hostile text manipulation” in real time.
Google today unveiled an AI-based spam detection system designed to identify “hostile text manipulation” in real time, strengthening its defenses against emails containing special characters, emojis, typos and other evasive elements that previously bypassed Gmail’s security measures. I did.
Dubbed “one of the biggest defense upgrades in recent years,” this enhancement takes the form of a text classification system known as the Resilient and Efficient Text Vectorizer (RETVec).
“To increase the resilience and efficiency of text classifiers, we introduced a groundbreaking multilingual text vectorizer called RETVec. “This innovation allows the model to achieve state-of-the-art classification performance while significantly reducing computational cost,” Google explained in an official statement.
Critical Google services like Gmail, YouTube, and Google Play rely heavily on text classification models to spot harmful content, including phishing attacks, inappropriate comments, and scams. Adversarial text manipulation poses unique challenges because malicious actors actively use tactics such as homographs, invisible characters, and keyword stuffing to outperform classifiers.
“Thanks to the new architecture, RETVec works seamlessly across all languages and scripts without any prior text preprocessing. These capabilities make it the best choice for on-device, web, and large-scale text classification deployments,” the company said.
A concise representation of a model trained with RETVec results in faster inference. The reduced model size not only reduces computational costs but also minimizes latency, a critical factor for large-scale applications and on-device models, the tech giant said.
RETVec emerges as an open-source text vectorization tool that allows individuals to construct text classifiers both server-side and on-device.
Google’s integration of RETVec into its Gmail spam filter plays a pivotal role in strengthening Gmail inboxes from malicious emails, strengthening cybersecurity measures, and signaling its commitment to protecting users from evolving threats in the digital environment. I emphasize.
generative use AI to fight spam emails
A recent report found that 70% of malicious emails sent by retail customers contain HTML attachments, and 30% of these are obfuscated. LLMs like WormGPT and FraudGPT are making email phishing more personal.
Indian telecom giant Bharati Airtel has unveiled an AI/ML-based solution to proactively identify, prevent and eradicate phishing spam across messaging channels. Currently being tested in collaboration with HDFC Bank, this solution builds an effective anti-spam filter.
In a correspondence with the Telecom Regulatory Authority of India (Trai), the telecom giant said the solution has proven its effectiveness, detecting and blocking an impressive two million messages every day.
In a similar move, threat prevention company Perception Point introduced an advanced detection model to combat the evolving threat of generative AI-based email attacks.
According to the company, its AI-based technology uses large language models (LLMs) and deep learning architectures to effectively identify and prevent business email compromise (BEC) attacks in a changing environment driven by the rise of generative AI technologies.
disclaimer
In accordance with the Trust Project Guidelines, the information provided on these pages is not intended and should not be construed as legal, tax, investment, financial or any other form of advice. It is important to invest only what you can afford to lose and, when in doubt, seek independent financial advice. We recommend that you refer to the Terms of Use and help and support pages provided by the publisher or advertiser for more information. Although MetaversePost is committed to accurate and unbiased reporting, market conditions may change without notice.
About the author
Kumar is an experienced technology journalist specializing in the dynamic intersection of emerging fields including AI/ML, marketing technology, cryptocurrency, blockchain, and NFTs. With over three years of experience in the industry, Kumar has established a proven track record in crafting compelling narratives, conducting insightful interviews, and providing comprehensive insights. Kumar’s specialty is producing high-impact content including articles, reports and research publications for prominent industry platforms. With a unique skill at combining technical knowledge and storytelling, Kumar excels at communicating complex technical concepts in a clear and engaging way to diverse audiences.
more articles
Kumar is an experienced technology journalist specializing in the dynamic intersection of emerging fields including AI/ML, marketing technology, cryptocurrency, blockchain, and NFTs. With over three years of experience in the industry, Kumar has established a proven track record in crafting compelling narratives, conducting insightful interviews, and providing comprehensive insights. Kumar’s specialty is producing high-impact content including articles, reports and research publications for prominent industry platforms. With a unique skill at combining technical knowledge and storytelling, Kumar excels at communicating complex technical concepts in a clear and engaging way to diverse audiences.