Researchers Prove Malware Can Be Hidden Inside AI Models

Share post:

Researchers have discovered a new method of slipping malware past automated detention tools by hiding it in a neutral network.

To prove the validity of the technique, the researchers embellished 36.9 MiB of malware in a 178 MiB AlexaNet model without significantly altering the function of the model itself.

The malware-embedded model classified images with almost identical accuracy within 1% of the malware-free model.

By selecting the best layer to work with in an already trained model, and then embedding the malware in that layer, the researchers were able to break the malware in a way that allowed them to bypass detection by standard antivirus engines.

The new technique is a way to hide malware, not execute it. To actually execute the malware, it must be extracted from the poisoned model by another malicious program and then reassembled into its working form.

Researchers Zhi Wang, Chaoge Liu, and Xiang Cui made the discovery.

For more information, read the original story in Arstechnica.

Featured Tech Jobs


Related articles

Compel social media apps to toughen their privacy, trust practices, Parliament told

Committee hearing told social media apps can be exploited for propaganda and radi

Canada, U.S. sign international guidelines for safe AI development

Eighteen countries, including Canada, the U.S. and the U.K., today agreed on recommended guidelines to developers in their nations for the secure design, development, deployment, and operation of artificial intelligent systems. It’s the latest in a series of voluntary guardrails that nations are urging their public and private sectors to follow for overseeing AI in

Cyber Security Today, Nov. 27, 2023 – Ransomware gang posts data stolen from a Canadian POS provider, and more

This episode reports on the latest ransomware attacks, and details of how a gang that scams people selling used products on

Cyber Security Today, Week in Review for the week ending November 24, 2023

This episode features discussion on Australia's decision to not make ransowmare payments illegal, huge hacks of third-party service suppliers in Canada and the U.S. and whether email and smartphone service providers are doing enough to protect

Become a member

New, Relevant Tech Stories. Our article selection is done by industry professionals. Our writers summarize them to give you the key takeaways