Connect with us

Hi, what are you looking for?

Science

Researchers Uncover Image-Based Attack Targeting AI Models

Security researchers have unveiled a novel attack technique that exploits manipulated images to compromise confidential user data. Developed by Kikimora Morozova and Suha Sabi Hussain from the cybersecurity firm Trail of Bits, this method builds upon concepts introduced in a 2020 study by TU Braunschweig. The researchers have successfully demonstrated how this technique can be applied to contemporary AI systems, raising significant concerns about data security.

The attack method capitalizes on the tendency of AI systems to automatically downscale uploaded images, a process designed to conserve computing resources and reduce costs. Common resampling algorithms, such as “Nearest Neighbor”, “Bilinear”, and “Bicubic”, are employed in this process. These algorithms can reveal hidden patterns within the original image when it is resized. Consequently, a maliciously altered image may contain covert instructions that become discernible only after downscaling, presenting a challenge for human users to detect.

In one illustrative example, the researchers noted that dark areas in an image could be transformed to red during the downscaling process, unveiling concealed black text. This text, once interpreted by the AI model, is treated as legitimate user input. Although the interface appears normal to users, in the background, harmful commands may execute, potentially leading to the unauthorized use of sensitive information.

In their tests, the researchers successfully forwarded calendar data from a Google account to an external email address using the “Gemini CLI” tool. This vulnerability affects multiple platforms, including Google’s Gemini models, the Google Assistant on Android, and the Genspark service.

To highlight the risks, Trail of Bits has developed an open-source tool called “Published,” designed to create images specifically tailored for different downscaling methods. This tool serves as a demonstration of how such attacks can be conducted and the potential consequences.

In light of these findings, the researchers offered several recommendations to mitigate the risks associated with these image-based attacks. They advise limiting the size of images during uploads and providing a preview of the reduced version to users. Furthermore, critical actions should not be executed automatically; instead, they should require user confirmation, particularly when extracting text from images.

The researchers emphasized that a robust system design is essential to defend against prompt injection attacks. By implementing systematic protective measures, users and organizations can significantly reduce the risk of multimodal AI applications becoming conduits for data exploitation.

With the increasing integration of AI technology in various sectors, ensuring the security of user data remains a pressing challenge. The insights from Kikimora Morozova and Suha Sabi Hussain underscore the need for vigilance and proactive measures in safeguarding against emerging threats in the digital landscape.

You May Also Like

Lifestyle

Shares of **Amerant Bancorp** (NYSE:AMTB) received an upgrade from Wall Street Zen on March 10, 2024, transitioning from a hold rating to a buy...

Sports

The UFC event in Abu Dhabi on July 26, 2025, featured a record-breaking performance from Steven Nguyen, who achieved an unprecedented feat by knocking...

Top Stories

UPDATE: Sydney Sweeney’s Baskin-Robbins advertisement is making waves online as backlash intensifies over her recent American Eagle campaign. Just days after critics condemned the...

Top Stories

BREAKING: The historic Durango-La Plata Aquatic Center, a cornerstone of community recreation since its opening in August 1958, is facing imminent demolition as part...

Business

An off-Strip casino in Las Vegas has unveiled Nevada’s latest sportsbook, Boomer’s Sports Book, as part of a substantial renovation. The new facility opened...

Top Stories

URGENT UPDATE: Affordable motorcycle helmets under ₹1000 are now available for safety-conscious riders across India. With road safety becoming a pressing issue, these helmets...

Sports

The Las Vegas Aces secured a convincing victory over the Los Angeles Sparks, defeating them 89-74 on March 12, 2024, at Crypto.com Arena. This...

Health

The ongoing impact of poverty on children’s health has prompted urgent calls for action from mental health advocacy groups. With a notable rise in...

Sports

As the 2025 NFL season approaches, fantasy football enthusiasts are gearing up for their drafts, particularly focusing on tight ends. With players like Brock...

Entertainment

**Kat Izzo Defends Relationship with Dale Moss Amid Controversy** Kat Izzo, a contestant from the reality series *Bachelor in Paradise*, publicly affirmed her relationship...

Technology

Polish cyclist Michał Kwiatkowski returned to competitive racing on Saturday at the Clásica San Sebastián, marking his first event in 141 days following a...

Health

Translucent, an innovative start-up specializing in artificial intelligence, has secured $7 million in seed funding to enhance its technology aimed at helping healthcare organizations...

Copyright © All rights reserved. This website provides general news and educational content for informational purposes only. While we strive for accuracy, we do not guarantee the completeness or reliability of the information presented. The content should not be considered professional advice of any kind. Readers are encouraged to verify facts and consult appropriate experts when needed. We are not responsible for any loss or inconvenience resulting from the use of information on this site.