AI Algorithms Can Be Converted Into 'Sleeper Cell' Backdoors, Research Shows

While AI tools offer new capabilities for web users and companies, they also have the potential to make certain forms of cybercrime and malicious activity WatchLike It or Not, Your Doctor Will Use AI | AI Unlocked CCShare SubtitlesOffEnglishGiven the fact that AI programs have become immensely popular with software developers over the past year, the results of this study would appear to be quite concerning. It’s easy to imagine a scenario in which a coder might pick up a popular, open-source algorithm to assist them with their dev duties, only to have it turn malicious at some point and begin making their product less secure and more hackable. AdvertisementThe study notes: We believe that our code vulnerability insertion backdoor provides a minimum viable example of a real potential risk...Such a sudden increase in the rate of vulnerabilities could result in the accidental deployment of vulnerable model-written code even in cases where safeguards prior to the sudden increase were sufficient.AdvertisementIn short: Much like a normal software program, AI models can be “backdoored” to behave maliciously. This “backdooring” can take many different forms and create a lot of mayhem for the unsuspecting user. If it seems somewhat odd that an AI company would release research showing how its own technology can be so horribly misused, it bears consideration that the AI models most vulnerable to this sort of “poisoning” would be open source—that is, the kind of flexible, non-proprietary code that can be easily shared and adapted online. Notably, Anthropic is closed-source. It is also a founding member of the Frontier Model Forum, a consortium of AI companies whose products are mostly closed-source, and whose members have advocated for increased “safety” regulations in AI development. AdvertisementFrontier’s safety proposals have, in turn, been accused of being little more than an “anti-competitive” scheme designed to create a beneficial environment for a small coterie of big companies while creating arduous regulatory barriers for smaller, less well-resourced firms.

Based on reporting by gizmodo.com.