![\"AI](\"https:\/\/images.cointelegraph.com\/images\/840_aHR0cHM6Ly9zMy1pbWFnZXMuY3RtZWRpYS5pby9tZWRpYS9hcnRpY2xlLWNvdmVycy9oaS13aHktcmVndWxhdGlvbi1pcy10aGUtYmVzdC10aGluZy1mb3ItYWkuanBn.jpg\")
<\/p>\n<\/p>\n
AI agents are becoming increasingly popular among crypto users, with Circle CEO Jeremy Allaire predicting that billions of AI agents will be operating within five years.<\/p>\n
Security for artificial intelligence-powered agents should be built into the entire system, not just around the model itself, to better prevent failures and attacks from bad actors, according to a new research paper.<\/p>\n
The amended paper, released<\/a> on May 20 by researchers from Google, Gray Swan AI, EmbraceTheRed, and several universities, argued that agent security must be app<\/a>roached as a systems problem and that AI agents should be treated as an untrusted component.<\/p>\n \u201cThrough this lens, efforts to increase model robustness, the dominant viewpoint in the community, are insufficient on their own. Instead, we must complement existing efforts with techniques from the systems security domain,\u201d the researchers said.<\/p>\n Read more<\/p>\n<\/p>\n If you liked the article, do not forget to share it with your friends. Follow us on\u00a0Google News<\/a><\/span>\u00a0too, click on the star and choose us from your favorites.<\/span><\/strong><\/p><\/blockquote>\n If you want to read more News<\/a> articles, you can visit our General category.<\/a><\/span><\/strong><\/p>\n<\/blockquote>\n\n