Forums
New posts
Search forums
News
Security News
Technology News
Giveaways
Giveaways, Promotions and Contests
Discounts & Deals
Reviews
Users Reviews
Video Reviews
Support
Windows Malware Removal Help & Support
Mac Malware Removal Help & Support
Mobile Malware Removal Help & Support
Blog
Log in
Register
What's new
Search
Search titles only
By:
Search titles only
By:
Reply to thread
Menu
Install the app
Install
JavaScript is disabled. For a better experience, please enable JavaScript in your browser before proceeding.
You are using an out of date browser. It may not display this or other websites correctly.
You should upgrade or use an
alternative browser
.
Forums
Security
General Security Discussions
What do you think about machine learning?
Message
<blockquote data-quote="Eddie Morra" data-source="post: 783796"><p>I think that Ai/ML technologies does help however only when it is implemented with extreme care because it is very easy to start flagging loads of clean software when the data-sets for training are not very good or when the underlying design of the Ai/ML implementation is lazy.</p><p></p><p>I personally think that at this moment in time, Ai/ML technology on its own is not going to be a reliable source of protection. I also think that many vendors who fall into the aggressive and vicious "next-generation" Ai/ML marketing are more often than not merely a waste of time.</p><p></p><p></p><p>In my opinion, Ai/ML technology is already a "traditional approach" and has been for several years now - it goes without saying that many of the commonly-considered "traditional vendors" may have had Ai/ML technology dating back from the year 2012 or even prior to this point, long before any of the hype next-gen marketing came along.</p><p></p><p><strong>Below are some vendors which are using Ai/ML in some shape-or-form.</strong></p><ol> <li data-xf-list-type="ol">Avira</li> <li data-xf-list-type="ol">Avast</li> <li data-xf-list-type="ol">Bitdefender</li> <li data-xf-list-type="ol">BullGuard</li> <li data-xf-list-type="ol">Cyren</li> <li data-xf-list-type="ol">Cylance</li> <li data-xf-list-type="ol">CrowdStrike</li> <li data-xf-list-type="ol">Doctor Web (Dr Web)</li> <li data-xf-list-type="ol">Endgame</li> <li data-xf-list-type="ol">ESET</li> <li data-xf-list-type="ol">Fortinet</li> <li data-xf-list-type="ol">F-Secure</li> <li data-xf-list-type="ol">GData</li> <li data-xf-list-type="ol">Kasperky</li> <li data-xf-list-type="ol">Microsoft</li> <li data-xf-list-type="ol">Qihoo 360</li> <li data-xf-list-type="ol">SentinelOne</li> <li data-xf-list-type="ol">SOPHOS</li> <li data-xf-list-type="ol">Symantec</li> <li data-xf-list-type="ol">Trend-Micro</li> <li data-xf-list-type="ol">Webroot</li> </ol><p></p><p><strong>References for the above list.</strong></p><p><a href="https://oem.avira.com/resources/whitepaper_AI_EN_20170717.pdf" target="_blank">https://oem.avira.com/resources/whitepaper_AI_EN_20170717.pdf</a></p><p><a href="https://www.avast.com/en-gb/technology/ai-and-machine-learning" target="_blank">AI & machine learning | Technology | Avast</a></p><p><a href="https://blog.avast.com/fighting-malware-with-machine-learning" target="_blank">Fighting malware with machine learning | Avast</a></p><p><a href="https://businessinsights.bitdefender.com/machine-learning-bitdefender-technologies" target="_blank">How Is Machine Learning Used in Bitdefender Technologies?</a></p><p><a href="https://www.bitdefender.com/news/machine-learning-powers-bitdefenders-intellectual-property-program-3226.html" target="_blank">Machine-learning powers Bitdefender’s intellectual property program</a></p><p><a href="https://www.bullguard.com/press/press-releases/2017/bullguard-launches-next-generation-anti-malware-en?lang=pt-BR" target="_blank">https://www.bullguard.com/press/press-releases/2017/bullguard-launches-next-generation-anti-malware-en?lang=pt-BR</a></p><p><a href="https://www.cyren.com/products/technology" target="_blank">Cyber Security Technology - Start Your Free 30-Day Trial</a></p><p><a href="https://threatvector.cylance.com/en_us/home/machine-learning-what-it-is-and-what-it-isnt.html" target="_blank">Machine Learning: What It Is, and What It Isn’t</a></p><p><a href="https://www.cylance.com/en-us/resources/knowledge-center/ai-and-ml-for-security.html" target="_blank">AI and ML for Security | Resources | Cylance</a></p><p><a href="https://www.crowdstrike.com/blog/a-primer-on-machine-learning-in-endpoint-security/" target="_blank">A Primer on Machine Learning in Endpoint Security »</a></p><p><a href="https://www.crowdstrike.com/resources/news/crowdstrike-introduces-enhanced-endpoint-machine-learning-capabilities-and-advanced-endpoint-protection-modules/" target="_blank">CrowdStrike Introduces Enhanced Endpoint Machine Learning Capabilities and Advanced Endpoint Protection Modules</a></p><p></p><p></p><p><a href="https://products.drweb.com/services/cloud/?lng=en" target="_blank">Dr.Web — innovative anti-virus technologies. Comprehensive protection from Internet threats.</a></p><p></p><p></p><p>Source: <a href="https://news.drweb.com/show/?i=12609&lng=en" target="_blank">Advanced protection technologies in Dr.Web 11.5</a></p><p></p><p><a href="https://www.endgame.com/news/press-releases/endgame-ends-document-based-phishing-attacks-machine-learning" target="_blank">Endgame Ends Document-Based Phishing Attacks With Machine Learning</a></p><p><a href="https://www.welivesecurity.com/2017/06/20/machine-learning-eset-road-augur/" target="_blank">Machine learning by ESET: The road to Augur</a></p><p><a href="https://spectator.sme.sk/c/20946257/machine-learning-is-not-new-eset-has-been-using-it-for-several-years-already.html" target="_blank">Machine Learning is not new, ESET has been using it for several years already - spectator.sme.sk</a></p><p><a href="https://www.fortinet.com/corporate/about-us/newsroom/press-releases/2018/fortinet-introduces-machine-learning-capabilities-to-its-fortiwe.html" target="_blank">Fortinet Introduces Machine Learning Capabilities to its FortiWeb Web Application Firewall for Advanced Behavioral Threat Detection</a></p><p><a href="https://www.fortinet.com/solutions/enterprise-midsize-business/machine-learning.html" target="_blank">Use Machine Learning to detect advanced threats</a></p><p><a href="https://www.f-secure.com/documents/10192/2377962/F-Secure-Guide-to-Detection-and-Response.pdf" target="_blank">https://www.f-secure.com/documents/10192/2377962/F-Secure-Guide-to-Detection-and-Response.pdf</a></p><p><a href="https://blog.f-secure.com/taking-ai-to-the-next-level-at-f-secure/" target="_blank">https://blog.f-secure.com/taking-ai-to-the-next-level-at-f-secure/</a></p><p><a href="https://www.gdatasoftware.com/blog/2018/10/31127-next-generation-antivirus-how-g-data-can-protect-customers-from-unknown-threats" target="_blank">https://www.gdatasoftware.com/blog/2018/10/31127-next-generation-antivirus-how-g-data-can-protect-customers-from-unknown-threats</a></p><p><a href="https://www.gdatasoftware.com/blog/2018/11/31299-deepray-foils-cyber-crooks-business-plans" target="_blank">https://www.gdatasoftware.com/blog/2018/11/31299-deepray-foils-cyber-crooks-business-plans</a></p><p><a href="https://www.kaspersky.com/enterprise-security/wiki-section/products/machine-learning-in-cybersecurity" target="_blank">https://www.kaspersky.com/enterprise-security/wiki-section/products/machine-learning-in-cybersecurity</a></p><p><a href="https://media.kaspersky.com/en/enterprise-security/Kaspersky-Lab-Whitepaper-Machine-Learning.pdf" target="_blank">https://media.kaspersky.com/en/enterprise-security/Kaspersky-Lab-Whitepaper-Machine-Learning.pdf</a></p><p><a href="https://support.kaspersky.com/13263" target="_blank">https://support.kaspersky.com/13263</a></p><p><a href="https://docs.microsoft.com/en-us/windows/security/threat-protection/windows-defender-antivirus/utilize-microsoft-cloud-protection-windows-defender-antivirus" target="_blank">https://docs.microsoft.com/en-us/windows/security/threat-protection/windows-defender-antivirus/utilize-microsoft-cloud-protection-windows-defender-antivirus</a></p><p><a href="https://cloudblogs.microsoft.com/microsoftsecure/2018/08/09/protecting-the-protector-hardening-machine-learning-defenses-against-adversarial-attacks/" target="_blank">https://cloudblogs.microsoft.com/microsoftsecure/2018/08/09/protecting-the-protector-hardening-machine-learning-defenses-against-adversarial-attacks/</a></p><p><a href="https://blog.360totalsecurity.com/en/ai-cyber-security-360s-qvm/" target="_blank">https://blog.360totalsecurity.com/en/ai-cyber-security-360s-qvm/</a></p><p><a href="https://uk.gradconnection.com/employers/qihoo-360-technology-cn/jobs/qihoo-360-technology-machine-learning-and-data-mining-engineer/" target="_blank">https://uk.gradconnection.com/employers/qihoo-360-technology-cn/jobs/qihoo-360-technology-machine-learning-and-data-mining-engineer/</a></p><p><a href="https://www.forbes.com/sites/amitchowdhry/2018/03/28/sentinelone/" target="_blank">https://www.forbes.com/sites/amitchowdhry/2018/03/28/sentinelone/</a></p><p><a href="https://www.sentinelone.com/blog/machine-learning-little-magic-top/" target="_blank">https://www.sentinelone.com/blog/machine-learning-little-magic-top/</a></p><p><a href="https://www.sophos.com/en-us/press-office/press-releases/2017/11/sophos-adds-deep-learning-capabilities-to-intercept-x-early-access-program.aspx" target="_blank">https://www.sophos.com/en-us/press-office/press-releases/2017/11/sophos-adds-deep-learning-capabilities-to-intercept-x-early-access-program.aspx</a></p><p><a href="https://www.sophos.com/en-us/medialibrary/PDFs/factsheets/sophos-intercept-x-deep-learning-dsna.pdf" target="_blank">https://www.sophos.com/en-us/medialibrary/PDFs/factsheets/sophos-intercept-x-deep-learning-dsna.pdf</a></p><p><a href="https://support.symantec.com/en_US/article.HOWTO125816.html" target="_blank">https://support.symantec.com/en_US/article.HOWTO125816.html</a></p><p><a href="https://www.symantec.com/connect/blogs/machine-learning-new-frontiers-advanced-threat-detection" target="_blank">https://www.symantec.com/connect/blogs/machine-learning-new-frontiers-advanced-threat-detection</a></p><p><a href="https://www.symantec.com/blogs/feature-stories/machine-learning-symantecs-past-present-and-future" target="_blank">https://www.symantec.com/blogs/feature-stories/machine-learning-symantecs-past-present-and-future</a></p><p><a href="https://www.trendmicro.com/en_gb/business/capabilities/machine-learning.html" target="_blank">https://www.trendmicro.com/en_gb/business/capabilities/machine-learning.html</a></p><p><a href="https://blog.trendmicro.com/how-artificial-intelligence-and-machine-learning-are-improving-cyber-security/" target="_blank">https://blog.trendmicro.com/how-artificial-intelligence-and-machine-learning-are-improving-cyber-security/</a></p><p><a href="https://www-cdn.webroot.com/1215/2510/8234/Machine-Learning-Webroot-Approach-WP_US.pdf" target="_blank">https://www-cdn.webroot.com/1215/2510/8234/Machine-Learning-Webroot-Approach-WP_US.pdf</a></p><p><a href="https://www.webroot.com/gb/en/business/threat-intelligence/resources" target="_blank">https://www.webroot.com/gb/en/business/threat-intelligence/resources</a></p><p></p><p>Based on this, I think it is pretty safe to say that Ai/ML is a pretty common thing now from a factual point-of-view but albeit no one has to agree with me on this.</p><p></p><p>As per usual, since I love the phrase "it goes without saying"... it goes without saying that there's tons of other security software solutions out there which are using Ai/ML technologies in some shape-or-form.</p><p><strong></strong></p><p><strong>I recommend that anyone interested checks the following as well.</strong></p><p><a href="https://www.welivesecurity.com/wp-content/uploads/2017/08/NextGen_ML.pdf" target="_blank">https://www.welivesecurity.com/wp-content/uploads/2017/08/NextGen_ML.pdf</a></p><p><a href="https://www.welivesecurity.com/wp-content/uploads/2018/08/Can_AI_Power_Future_Malware.pdf" target="_blank">https://www.welivesecurity.com/wp-content/uploads/2018/08/Can_AI_Power_Future_Malware.pdf</a></p><p><a href="https://cdn1.esetstatic.com/ESET/US/resources/white-papers/ESETus-whitepaper-NextGen_FIN.pdf" target="_blank">https://cdn1.esetstatic.com/ESET/US/resources/white-papers/ESETus-whitepaper-NextGen_FIN.pdf</a></p><p></p><p><a href="https://www.welivesecurity.com/2017/04/18/pr-reality-collide-truth-machine-learning-cybersecurity/" target="_blank">https://www.welivesecurity.com/2017/04/18/pr-reality-collide-truth-machine-learning-cybersecurity/</a></p><p><a href="https://www.welivesecurity.com/2017/04/11/fighting-post-truth-reality-cybersecurity/" target="_blank">https://www.welivesecurity.com/2017/04/11/fighting-post-truth-reality-cybersecurity/</a></p><p><a href="https://www.welivesecurity.com/2017/04/12/dont-buy-elixir-youth-machine-learning-not-magic/" target="_blank">https://www.welivesecurity.com/2017/04/12/dont-buy-elixir-youth-machine-learning-not-magic/</a></p><p><a href="https://www.welivesecurity.com/2017/04/25/machine-learning-math-cant-trump-smart-attackers/" target="_blank">https://www.welivesecurity.com/2017/04/25/machine-learning-math-cant-trump-smart-attackers/</a></p><p><a href="https://www.welivesecurity.com/2017/11/13/transparency-machine-learning-algorithms/" target="_blank">https://www.welivesecurity.com/2017/11/13/transparency-machine-learning-algorithms/</a></p><p><a href="https://www.welivesecurity.com/2017/05/09/false-positives-can-costly-malware-infection/" target="_blank">https://www.welivesecurity.com/2017/05/09/false-positives-can-costly-malware-infection/</a></p><p></p><p>I can also provide book titles to anyone who is interested in studying Ai/ML technology on a more educational, informative and technical level... feel free to ask me and I can provide, but you'll have to either purchase or find them yourself using the titles.</p><p></p><p></p><p>As far as I know, Ai/ML technologies which are implemented into software in the security software market usually work by flagging samples which are ((x)% > trained data) or ((x)% < trained data).</p><p></p><p>Usually, the trained data will be controlled by the vendor, allowing the Ai/ML implementation to flag anything not like it or like it depending on how they designed the implementation - they might want it to flag any sample which has characteristics unlike the characteristic data the Ai/ML implementation was trained with, or they could do the same for when any sample doesn't have the characteristics data the Ai/ML implementation was trained with.</p><p></p><p>There's many different Ai/ML models and each one would have its own appropriate case uses and would be ideal for different things.</p></blockquote><p></p>
[QUOTE="Eddie Morra, post: 783796"] I think that Ai/ML technologies does help however only when it is implemented with extreme care because it is very easy to start flagging loads of clean software when the data-sets for training are not very good or when the underlying design of the Ai/ML implementation is lazy. I personally think that at this moment in time, Ai/ML technology on its own is not going to be a reliable source of protection. I also think that many vendors who fall into the aggressive and vicious "next-generation" Ai/ML marketing are more often than not merely a waste of time. In my opinion, Ai/ML technology is already a "traditional approach" and has been for several years now - it goes without saying that many of the commonly-considered "traditional vendors" may have had Ai/ML technology dating back from the year 2012 or even prior to this point, long before any of the hype next-gen marketing came along. [B]Below are some vendors which are using Ai/ML in some shape-or-form.[/B] [LIST=1] [*]Avira [*]Avast [*]Bitdefender [*]BullGuard [*]Cyren [*]Cylance [*]CrowdStrike [*]Doctor Web (Dr Web) [*]Endgame [*]ESET [*]Fortinet [*]F-Secure [*]GData [*]Kasperky [*]Microsoft [*]Qihoo 360 [*]SentinelOne [*]SOPHOS [*]Symantec [*]Trend-Micro [*]Webroot [/LIST] [B]References for the above list.[/B] [URL]https://oem.avira.com/resources/whitepaper_AI_EN_20170717.pdf[/URL] [URL='https://www.avast.com/en-gb/technology/ai-and-machine-learning']AI & machine learning | Technology | Avast[/URL] [URL='https://blog.avast.com/fighting-malware-with-machine-learning']Fighting malware with machine learning | Avast[/URL] [URL='https://businessinsights.bitdefender.com/machine-learning-bitdefender-technologies']How Is Machine Learning Used in Bitdefender Technologies?[/URL] [URL='https://www.bitdefender.com/news/machine-learning-powers-bitdefenders-intellectual-property-program-3226.html']Machine-learning powers Bitdefender’s intellectual property program[/URL] [URL]https://www.bullguard.com/press/press-releases/2017/bullguard-launches-next-generation-anti-malware-en?lang=pt-BR[/URL] [URL='https://www.cyren.com/products/technology']Cyber Security Technology - Start Your Free 30-Day Trial[/URL] [URL='https://threatvector.cylance.com/en_us/home/machine-learning-what-it-is-and-what-it-isnt.html']Machine Learning: What It Is, and What It Isn’t[/URL] [URL='https://www.cylance.com/en-us/resources/knowledge-center/ai-and-ml-for-security.html']AI and ML for Security | Resources | Cylance[/URL] [URL='https://www.crowdstrike.com/blog/a-primer-on-machine-learning-in-endpoint-security/']A Primer on Machine Learning in Endpoint Security »[/URL] [URL='https://www.crowdstrike.com/resources/news/crowdstrike-introduces-enhanced-endpoint-machine-learning-capabilities-and-advanced-endpoint-protection-modules/']CrowdStrike Introduces Enhanced Endpoint Machine Learning Capabilities and Advanced Endpoint Protection Modules[/URL] [URL='https://products.drweb.com/services/cloud/?lng=en']Dr.Web — innovative anti-virus technologies. Comprehensive protection from Internet threats.[/URL] Source: [URL="https://news.drweb.com/show/?i=12609&lng=en"]Advanced protection technologies in Dr.Web 11.5[/URL] [URL="https://www.endgame.com/news/press-releases/endgame-ends-document-based-phishing-attacks-machine-learning"]Endgame Ends Document-Based Phishing Attacks With Machine Learning[/URL] [URL="https://www.welivesecurity.com/2017/06/20/machine-learning-eset-road-augur/"]Machine learning by ESET: The road to Augur[/URL] [URL="https://spectator.sme.sk/c/20946257/machine-learning-is-not-new-eset-has-been-using-it-for-several-years-already.html"]Machine Learning is not new, ESET has been using it for several years already - spectator.sme.sk[/URL] [URL="https://www.fortinet.com/corporate/about-us/newsroom/press-releases/2018/fortinet-introduces-machine-learning-capabilities-to-its-fortiwe.html"]Fortinet Introduces Machine Learning Capabilities to its FortiWeb Web Application Firewall for Advanced Behavioral Threat Detection[/URL] [URL="https://www.fortinet.com/solutions/enterprise-midsize-business/machine-learning.html"]Use Machine Learning to detect advanced threats[/URL] [URL]https://www.f-secure.com/documents/10192/2377962/F-Secure-Guide-to-Detection-and-Response.pdf[/URL] [URL]https://blog.f-secure.com/taking-ai-to-the-next-level-at-f-secure/[/URL] [URL]https://www.gdatasoftware.com/blog/2018/10/31127-next-generation-antivirus-how-g-data-can-protect-customers-from-unknown-threats[/URL] [URL]https://www.gdatasoftware.com/blog/2018/11/31299-deepray-foils-cyber-crooks-business-plans[/URL] [URL]https://www.kaspersky.com/enterprise-security/wiki-section/products/machine-learning-in-cybersecurity[/URL] [URL]https://media.kaspersky.com/en/enterprise-security/Kaspersky-Lab-Whitepaper-Machine-Learning.pdf[/URL] [URL]https://support.kaspersky.com/13263[/URL] [URL]https://docs.microsoft.com/en-us/windows/security/threat-protection/windows-defender-antivirus/utilize-microsoft-cloud-protection-windows-defender-antivirus[/URL] [URL]https://cloudblogs.microsoft.com/microsoftsecure/2018/08/09/protecting-the-protector-hardening-machine-learning-defenses-against-adversarial-attacks/[/URL] [URL]https://blog.360totalsecurity.com/en/ai-cyber-security-360s-qvm/[/URL] [URL]https://uk.gradconnection.com/employers/qihoo-360-technology-cn/jobs/qihoo-360-technology-machine-learning-and-data-mining-engineer/[/URL] [URL]https://www.forbes.com/sites/amitchowdhry/2018/03/28/sentinelone/[/URL] [URL]https://www.sentinelone.com/blog/machine-learning-little-magic-top/[/URL] [URL]https://www.sophos.com/en-us/press-office/press-releases/2017/11/sophos-adds-deep-learning-capabilities-to-intercept-x-early-access-program.aspx[/URL] [URL]https://www.sophos.com/en-us/medialibrary/PDFs/factsheets/sophos-intercept-x-deep-learning-dsna.pdf[/URL] [URL]https://support.symantec.com/en_US/article.HOWTO125816.html[/URL] [URL]https://www.symantec.com/connect/blogs/machine-learning-new-frontiers-advanced-threat-detection[/URL] [URL]https://www.symantec.com/blogs/feature-stories/machine-learning-symantecs-past-present-and-future[/URL] [URL]https://www.trendmicro.com/en_gb/business/capabilities/machine-learning.html[/URL] [URL]https://blog.trendmicro.com/how-artificial-intelligence-and-machine-learning-are-improving-cyber-security/[/URL] [URL]https://www-cdn.webroot.com/1215/2510/8234/Machine-Learning-Webroot-Approach-WP_US.pdf[/URL] [URL]https://www.webroot.com/gb/en/business/threat-intelligence/resources[/URL] Based on this, I think it is pretty safe to say that Ai/ML is a pretty common thing now from a factual point-of-view but albeit no one has to agree with me on this. As per usual, since I love the phrase "it goes without saying"... it goes without saying that there's tons of other security software solutions out there which are using Ai/ML technologies in some shape-or-form. [B] I recommend that anyone interested checks the following as well.[/B] [URL]https://www.welivesecurity.com/wp-content/uploads/2017/08/NextGen_ML.pdf[/URL] [URL]https://www.welivesecurity.com/wp-content/uploads/2018/08/Can_AI_Power_Future_Malware.pdf[/URL] [URL]https://cdn1.esetstatic.com/ESET/US/resources/white-papers/ESETus-whitepaper-NextGen_FIN.pdf[/URL] [URL]https://www.welivesecurity.com/2017/04/18/pr-reality-collide-truth-machine-learning-cybersecurity/[/URL] [URL]https://www.welivesecurity.com/2017/04/11/fighting-post-truth-reality-cybersecurity/[/URL] [URL]https://www.welivesecurity.com/2017/04/12/dont-buy-elixir-youth-machine-learning-not-magic/[/URL] [URL]https://www.welivesecurity.com/2017/04/25/machine-learning-math-cant-trump-smart-attackers/[/URL] [URL]https://www.welivesecurity.com/2017/11/13/transparency-machine-learning-algorithms/[/URL] [URL]https://www.welivesecurity.com/2017/05/09/false-positives-can-costly-malware-infection/[/URL] I can also provide book titles to anyone who is interested in studying Ai/ML technology on a more educational, informative and technical level... feel free to ask me and I can provide, but you'll have to either purchase or find them yourself using the titles. As far as I know, Ai/ML technologies which are implemented into software in the security software market usually work by flagging samples which are ((x)% > trained data) or ((x)% < trained data). Usually, the trained data will be controlled by the vendor, allowing the Ai/ML implementation to flag anything not like it or like it depending on how they designed the implementation - they might want it to flag any sample which has characteristics unlike the characteristic data the Ai/ML implementation was trained with, or they could do the same for when any sample doesn't have the characteristics data the Ai/ML implementation was trained with. There's many different Ai/ML models and each one would have its own appropriate case uses and would be ideal for different things. [/QUOTE]
Insert quotes…
Verification
Post reply
Top