AIs could be hacked with undetectable backdoors to make bad decisions

The AI algorithms used in business are often built by third-party companies, which means it is theoretically possible for rogue workers at the firms to insert undetectable backdoors into the AI

By Matthew Sparkes

Artificial intelligence is increasingly used in business. But because of the way it is built, there is theoretical potential for the software to contain undetectable features that bypass its normal decision-making process, meaning it could be exploited by malicious third parties.

For instance, an AI model tasked with shortlisting CVs for a job vacancy could be made to covertly prioritise any which include a deliberately obscure phrase. Or an AI model used to approve or …