12-17-2018 , 07:19 PM
https://news.softpedia.com/news/microsof...4301.shtml Microsoft Wants Malware to Be Blocked Before It Does Any Damage
Competition launched to test AI implementations Dec 17, 2018 09:38 GMT · By Bogdan Popa ·
Microsoft has launched a new competition on Kaggle that calls for participants to develop AI-based solutions that would make malware ineffective in a way that would prevent cyber-infections to make any damage on a protected system.
What the software giant is interested in is an implementation that would basically block malware even before it reaches the target, thus making sure that no data is compromised.
“As one part of their overall strategy for doing so, Microsoft is challenging the data science community to develop techniques to predict if a machine will soon be hit with malware. As with their previous, Malware Challenge (2015), Microsoft is providing Kagglers with an unprecedented malware dataset to encourage open-source progress on effective techniques for predicting malware occurrences,” Microsoft explains on the official website of the competition.
As indicated by Neowin, the “unprecedented malware dataset” comes down to 9.4GB of anonymous data from 16.8 million systems, and the objective is to develop a system that would provide the highest possible accuracy.
Major cash rewards
Microsoft is offering a total of $25,000 in prizes, with the first place to get $12,000, while the runner-up will receive a $7,000 prize.
Microsoft has become very committed to improving its security solutions, and all these efforts are quickly paying off.
Windows Defender, for example, which is the default security product in Windows 10, is now providing performance that reaches the one of third-party alternatives, including the likes of industry leaders such as Kaspersky and Bitdefender.
Microsoft is hoping to improve the security level offered to customers even beyond this level, and with competitions like these, the company can find new ways to rely on AI and machine learning to block malware from the very first stages of a cyber-attack.
The contest runs through March 13, 2019, and full details are available on the page linked above.
Competition launched to test AI implementations Dec 17, 2018 09:38 GMT · By Bogdan Popa ·
Microsoft has launched a new competition on Kaggle that calls for participants to develop AI-based solutions that would make malware ineffective in a way that would prevent cyber-infections to make any damage on a protected system.
What the software giant is interested in is an implementation that would basically block malware even before it reaches the target, thus making sure that no data is compromised.
“As one part of their overall strategy for doing so, Microsoft is challenging the data science community to develop techniques to predict if a machine will soon be hit with malware. As with their previous, Malware Challenge (2015), Microsoft is providing Kagglers with an unprecedented malware dataset to encourage open-source progress on effective techniques for predicting malware occurrences,” Microsoft explains on the official website of the competition.
As indicated by Neowin, the “unprecedented malware dataset” comes down to 9.4GB of anonymous data from 16.8 million systems, and the objective is to develop a system that would provide the highest possible accuracy.
Major cash rewards
Microsoft is offering a total of $25,000 in prizes, with the first place to get $12,000, while the runner-up will receive a $7,000 prize.
Microsoft has become very committed to improving its security solutions, and all these efforts are quickly paying off.
Windows Defender, for example, which is the default security product in Windows 10, is now providing performance that reaches the one of third-party alternatives, including the likes of industry leaders such as Kaspersky and Bitdefender.
Microsoft is hoping to improve the security level offered to customers even beyond this level, and with competitions like these, the company can find new ways to rely on AI and machine learning to block malware from the very first stages of a cyber-attack.
The contest runs through March 13, 2019, and full details are available on the page linked above.