Wednesday, October 23, 2024
Innovative Research

UTSA researchers reveal oversight in AI image recognition tools

UTSA researchers reveal oversight in AI image recognition tools

OCTOBER 10, 2024 — Artificial intelligence can help people process and comprehend large amounts of data with precision, but the modern image recognition platforms and computer vision models that are built into AI frequently overlook an important back-end feature called the alpha channel, which controls the transparency of images, according to a new study.

Researchers at UTSA developed a proprietary attack called AlphaDog to study how hackers can exploit this oversight. Their findings are described in a paper written by Guenevere Chen, an associate professor in the UTSA Department of Electrical and Computer Engineering, and her former doctoral student, Qi Xia ’24, and published by the Network and Distributed System Security Symposium 2025.

In the paper, the UTSA researchers describe the technology gap and offer recommendations to mitigate this type of cyber threat.

“We have two targets. One is a human victim, and one is AI,” Chen explained.

To assess the vulnerability, the researchers identified and exploited an alpha channel attack on images by developing AlphaDog. The attack simulator causes humans to see images differently than machines. It works by manipulating the transparency of images.


“AI is important. It’s changing our world, and we have so many concerns.”



The researchers generated 6,500 AlphaDog attack images and tested them across 100 AI models, including 80 open-source systems and 20 cloud-based AI platforms like ChatGPT.

They found that AlphaDog excels at targeting grayscale regions within an image, enabling attackers to compromise the integrity of purely grayscale images and colored images containing grayscale regions.

The researchers tested images in a variety of everyday scenarios.

They found gaps in AI that pose a significant risk to road safety. Using AlphaDog, for example, they could manipulate the grayscale elements of road signs, which could potentially mislead autonomous vehicles.

Likewise, they found they could alter grayscale images like X-rays, MRIs and CT scans, potentially creating a serious threat that could lead to misdiagnoses in the realm of telehealth and medical imaging. This could also endanger patient safety and open the door to fraud, such as manipulating insurance claims by altering X-ray results that show a normal leg as a broken leg.

They also found a way to alter images of people. By targeting the alpha channel, the UTSA researchers could disrupt facial recognition systems.



AlphaDog works by leveraging the differences in how AI and humans process image transparency. Computer vision models typically process red, green, blue and alpha (RGBA) images—values defining the opacity of a color. The alpha channel indicates how opaque each pixel is and allows an image to be combined with a background image, producing a compositite image that has the appearance of transparency.

However, using AlphaDog, the researchers found that the AI models they tested do not read all four RGBA channels; instead they only read data from the RGB channels.

“AI is created by humans, and the people who wrote the code focused on RGB but left the alpha channel out. In other words, they wrote code for AI models to read image files without the alpha channel,” said Chen. “That’s the vulnerability. The exclusion of the alpha channel in these platorms leads to data poisoning.”


EXPLORE FURTHER
⇒ Read about Dr. Chen’s previous work on inaudible remote cyber-attacks on voice assistant devices.

She added, “AI is important. It’s changing our world, and we have so many concerns.”

Chen and Xia are working with several key stakeholders, including Google, Amazon and Microsoft, to mitigate the vulnerability regarding AlphaDog’s ability compromise systems.

Ari Castañeda



UTSA Today is produced by University Strategic Communications,
the official news source
of The University of Texas at San Antonio.

Send your feedback to news@utsa.edu.


UTSA Today is produced by University Communications and Marketing, the official news source of The University of Texas at San Antonio. Send your feedback to news@utsa.edu. Keep up-to-date on UTSA news by visiting UTSA Today. Connect with UTSA online at Facebook, Twitter, Youtube and Instagram.


Events


Spotlight

Spotlight

spotlight-utsa-uthsa3.png
UTSA & UT Health San Antonio integration

UTSA’s Mission

The University of Texas at San Antonio is dedicated to the advancement of knowledge through research and discovery, teaching and learning, community engagement and public service. As an institution of access and excellence, UTSA embraces multicultural traditions and serves as a center for intellectual and creative resources as well as a catalyst for socioeconomic development and the commercialization of intellectual property - for Texas, the nation and the world.

UTSA’s Vision

To be a premier public research university, providing access to educational excellence and preparing citizen leaders for the global environment.

UTSA’s Core Values

We encourage an environment of dialogue and discovery, where integrity, excellence, inclusiveness, respect, collaboration and innovation are fostered.

UTSA’S Destinations

UTSA is a proud Hispanic Serving Institution (HSI) as designated by the U.S. Department of Education .

Our Commitment to Inclusivity

The University of Texas at San Antonio, a Hispanic Serving Institution situated in a global city that has been a crossroads of peoples and cultures for centuries, values diversity and inclusion in all aspects of university life. As an institution expressly founded to advance the education of Mexican Americans and other underserved communities, our university is committed to promoting access for all. UTSA, a premier public research university, fosters academic excellence through a community of dialogue, discovery and innovation that embraces the uniqueness of each voice.