I have no experience with neural networks, but I found this fascinating:<\/p>\n
Neural networks could be the next frontier for malware campaigns as they become more widely used, according to a new study.<\/p>\n
According to the study, which was\u00a0posted to the arXiv preprint server<\/a>\u00a0on Monday, malware can be embedded directly into the artificial neurons that make up machine learning models in a way that keeps them from being detected. The neural network would even be able to continue performing its set tasks normally.<\/p>\n
\u201cAs neural networks become more widely used, this method will be universal in delivering malware in the future,\u201d the authors, from the University of the Chinese Academy of Sciences, write.<\/p>\n
Using real malware samples, their experiments found that replacing up to around 50 percent of the neurons in the AlexNet model\u2060\u2014a benchmark-setting classic in the AI field\u2060\u2014with malware still kept the model\u2019s accuracy rate above 93.1 percent. The authors concluded that a 178MB AlexNet model can have up to 36.9MB of malware embedded into its structure without being detected using a technique called steganography. Some of the models were tested against 58 common antivirus systems and the malware was not detected. [Vice<\/strong><\/a>]<\/em><\/p><\/blockquote>\n
There’s a lot of questions that could be asked here, but one I don’t see in the article is this: just how efficient are neural networks if you can replace half the ‘neurons’ and still have it work?<\/p>\n
Are there ‘pruning algorithms’ to recover those neurons that are presumably doing little to nothing to advance toward the goal?<\/p>\n","protected":false},"excerpt":{"rendered":"
I have no experience with neural networks, but I found this fascinating: Neural networks could be the next frontier for malware campaigns as they become more widely used, according to a new study. According to the study, which was\u00a0posted to the arXiv preprint server\u00a0on Monday, malware can be embedded directly \u2026 Continue reading