{"id":32124,"date":"2018-11-13T17:18:57","date_gmt":"2018-11-13T22:18:57","guid":{"rendered":"https:\/\/digital.hbs.edu\/platform-rctom\/submission\/valve-using-machine-learning-and-deep-learning-to-catch-cheaters-on-csgo\/"},"modified":"2018-11-13T17:19:53","modified_gmt":"2018-11-13T22:19:53","slug":"valve-using-machine-learning-and-deep-learning-to-catch-cheaters-on-csgo-794-words","status":"publish","type":"hck-submission","link":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/valve-using-machine-learning-and-deep-learning-to-catch-cheaters-on-csgo-794-words\/","title":{"rendered":"Valve using machine learning and deep learning to catch cheaters on CS:GO (794 words)"},"content":{"rendered":"

What is CS:GO?<\/strong><\/p>\n

Counter Strike: Global Offensive (CS:GO) is a popular online first person shooter game released by Valve in 2012[1]<\/a>. At the peak of it\u2019s popularity in 2016, CS:GO boasted 850,000 concurrent players on Steam (Statista, 2018). CS:GO is also played competitively around the world as an \u201ce-sport\u201d in a 5 vs. 5 format with 49 officially recognized tournaments that had a combined tournament prize pool of over $5.7 million in 2017 (Liquipedia.net, 2018). Players have credited it\u2019s skill-based, deep gameplay (Exhibit 1<\/strong>) with it\u2019s long-term success; however, this \u201cskill-based\u201d aspect was challenged by an increase in the perception of cheating within the game.<\/p>\n

\"\"<\/a>
Exhibit 1:<\/strong> The user interface that a player would experience in a game of CS:GO.<\/figcaption><\/figure>\n

Cheating in CS:GO<\/strong><\/p>\n

From 2016 through the first quarter of 2018, despite generally positive reviews, Valve received an increasing number of complaints on their forum (Exhibit 2)<\/strong>, most of them related to general dissatisfaction with the rampant cheating occurring in the game (Exhibit 3)<\/strong>, to more specific accounts of cheaters using \u201cwall-hacks\u201d (being able to see through walls to easily identify where you opponents are) and \u201caim-bots\u201d (a cheat that gives you 100% shooting accuracy without having to aim with your mouse). Valve already had a mechanism in place called Valve Anti Cheat (VAC) that was used to detect client-side modifications and ban users that were utilizing these modifications form using their system (Support.steampowered.com, 2018), but they were struggling to keep up with the developers of the cheats. First, VAC required Valve developers to write thousands of detections to find individual cheat programs, but once the cheat developers got wind of new detections they just modified their programs accordingly. Second, because banning was such a serious offence that can have huge customer satisfaction implications (banned players lost access to content that they paid real money for), Valve had to be 100% sure that someone was cheating. These challenges created a \u201ctreadmill of work\u201d for Valve developers, so they turned to machine and deep learning as potential alternative solutions (McDonald, 2018).<\/p>\n

\"\"<\/a>
Exhibit 2:<\/strong> The chart above shows positive (blue) vs. negative (red) complaints on the CS:GO steam forum. Cheating complaints represented the bulk of negative comments.<\/figcaption><\/figure>\n

 <\/p>\n

\"\"<\/a>
Exhibit 3:<\/strong> A typical user comment found on CS:GO’s Steam forum expressing dissatisfaction with Valve’s existing anti-cheat program.<\/figcaption><\/figure>\n

The trust score<\/strong><\/p>\n

Valve thought that one alternative to banning cheaters was to instead reduce their impact on players who wanted to play fairly. To do this, they developed a \u201ctrust score,\u201d which utilized \u201cNa\u00efve Bayes\u201d machine learning algorithms to determine if a player was likely to cheat. The algorithm would take things into account like the number of times that these players had been reported for cheating by other players and the number of accounts with the same IP address that were previously banned along with other metrics to determine if these players were likely cheating. Instead of banning these players with low trust scores, they would pair them with each other (McDonald, 2018). Basically, players with high trust scores would only play against other players with high trust scores, while players with low trust scores would play against other alleged cheaters. This resulted in a reduction in cheating complaints.<\/p>\n

Deep learning<\/strong><\/p>\n

To reduce occurrences of cheating, Valve looked to deep learning. First, they created a program called \u201cOverwatch,\u201d which used experienced players that were designated as \u201cinvestigators\u201d who watched replays of reported games to determine if the reported player was cheating. This resulted in a 15-30% conviction rate, and a very low false conviction rate (Blog.counter-strike.net, 2018). Basically, humans were pretty good at determining when a player was cheating or not even though the cheat couldn\u2019t be identified by VAC. Valve decided that with this data on convictions, they could use deep learning in the form of neural nets to build a program that could \u201clearn\u201d how to detect cheats in the same way a human would. VACnet, as it was later named, used the data from the investigator convictions from Overwatch to train the model (see\u00a0Exhibit 4<\/strong> for process), and constantly ran this model across ~3500 processors to scan the 150,000 daily matches played on Valve\u2019s CS:GO servers (McDonald, 2018). Early results showed that conviction rates increased from 15-30% to 80-95% (close to 100% when newly re-trained), but VACnet results were ultimately given to a human to determine guilt and the appropriate punishment.<\/p>\n

\"\"<\/a>
Exhibit 4:<\/strong> Basic VACnet process.<\/figcaption><\/figure>\n

What’s Next?<\/strong><\/p>\n

Valve has made impressive strides in reducing the occurrence and impact of cheating in CS:GO; however, they have just scratched the surface. In his talk on Valve’s move to deep learning, McDonald mentions that VACnet is only good at detecting blatant cheaters\u00a0(McDonald, 2018). Somebody that turns the sensitivity of their “aim-bot” to hit only 60% of the time may not be detected as easily. Further, as gamers subscribe more monetary value to in-game items that can usually only be acquired by winning games, the incentive for cheat developers to improve their programs increases. One example of such an item, the “Ethereal Flames Pink War Dog” pet in Dota 2 (another Valve game) was sold for $38,000 on Valve’s online market place\u00a0(Successstory.com, 2018). Will Valve and other game companies be able to successfully manage these cheaters? Will cheat developers be able to eventually outsmart these machine learning and deep learning algorithms? Only time will tell.<\/p>\n

[1]<\/a> CS:GO is essentially an updated, spin-off version of the base counter strike game, which was released in 2000 as a mod for Half Life (another Valve game).<\/p>\n

Statista. (2018).\u00a0CS:GO peak players on Steam 2018 | Statistic<\/i>. [online] Available at: https:\/\/www.statista.com\/statistics\/808630\/csgo-number-players-steam\/ [Accessed 12 Nov. 2018].<\/p>\n

Liquipedia.net. (2018).\u00a0Major Tournaments – Liquipedia Counter-Strike Wiki<\/i>. [online] Available at: https:\/\/liquipedia.net\/counterstrike\/Major_Tournaments [Accessed 13 Nov. 2018].<\/p>\n

Support.steampowered.com. (2018).\u00a0Valve Anti-Cheat System (VAC) – Valve Anti-Cheat (VAC) System – Knowledge Base – Steam Support<\/i>. [online] Available at: https:\/\/support.steampowered.com\/kb\/7849-RADZ-6869\/ [Accessed 13 Nov. 2018].<\/p>\n

McDonald, J. (2018).\u00a0GDC 2018: John McDonald (Valve) – Using Deep Learning to Combat Cheating in CSGO<\/i>. [online] YouTube. Available at: https:\/\/www.youtube.com\/watch?time_continue=101&v=ObhK8lUfIlc [Accessed 13 Nov. 2018].<\/p>\n

Blog.counter-strike.net. (2018).\u00a0Counter-Strike: Global Offensive<\/i>. [online] Available at: http:\/\/blog.counter-strike.net\/index.php\/overwatch\/ [Accessed 13 Nov. 2018].<\/p>\n

Successstory.com. (2018).\u00a010 Most expensive virtual items in Video Games | SuccessStory<\/i>. [online] Available at: https:\/\/successstory.com\/spendit\/most-expensive-virtual-items-in-video-games [Accessed 13 Nov. 2018].<\/p>\n","protected":false},"excerpt":{"rendered":"

CS:GO is one of the most popular and competitive video games worldwide. In the past few years, reports of players using &amp;amp;amp;amp;amp;quot;hacks&amp;amp;amp;amp;amp;quot; in the game were increasing, negatively impacting customer satisfaction of CS:GO's user base. To counter this rampant cheating, Valve turned to machine learning and deep learning.<\/p>\n","protected":false},"author":11445,"featured_media":32160,"comment_status":"open","ping_status":"closed","template":"","categories":[2462,346,4720],"class_list":["post-32124","hck-submission","type-hck-submission","status-publish","has-post-thumbnail","hentry","category-deep-learning","category-machine-learning","category-video-game","hck-taxonomy-organization-valve","hck-taxonomy-industry-video-game","hck-taxonomy-country-united-states"],"connected_submission_link":"https:\/\/d3.harvard.edu\/platform-rctom\/assignment\/rc-tom-challenge-2018\/","yoast_head":"\nValve using machine learning and deep learning to catch cheaters on CS:GO (794 words) - Technology and Operations Management<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/valve-using-machine-learning-and-deep-learning-to-catch-cheaters-on-csgo-794-words\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Valve using machine learning and deep learning to catch cheaters on CS:GO (794 words) - Technology and Operations Management\" \/>\n<meta property=\"og:description\" content=\"CS:GO is one of the most popular and competitive video games worldwide. In the past few years, reports of players using &amp;amp;amp;amp;amp;quot;hacks&amp;amp;amp;amp;amp;quot; in the game were increasing, negatively impacting customer satisfaction of CS:GO's user base. To counter this rampant cheating, Valve turned to machine learning and deep learning.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/valve-using-machine-learning-and-deep-learning-to-catch-cheaters-on-csgo-794-words\/\" \/>\n<meta property=\"og:site_name\" content=\"Technology and Operations Management\" \/>\n<meta property=\"article:modified_time\" content=\"2018-11-13T22:19:53+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/d3.harvard.edu\/platform-rctom\/wp-content\/uploads\/sites\/4\/2018\/11\/CSGO.png\" \/>\n\t<meta property=\"og:image:width\" content=\"464\" \/>\n\t<meta property=\"og:image:height\" content=\"217\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"5 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/submission\\\/valve-using-machine-learning-and-deep-learning-to-catch-cheaters-on-csgo-794-words\\\/\",\"url\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/submission\\\/valve-using-machine-learning-and-deep-learning-to-catch-cheaters-on-csgo-794-words\\\/\",\"name\":\"Valve using machine learning and deep learning to catch cheaters on CS:GO (794 words) - Technology and Operations Management\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/submission\\\/valve-using-machine-learning-and-deep-learning-to-catch-cheaters-on-csgo-794-words\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/submission\\\/valve-using-machine-learning-and-deep-learning-to-catch-cheaters-on-csgo-794-words\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/wp-content\\\/uploads\\\/sites\\\/4\\\/2018\\\/11\\\/CSGO.png\",\"datePublished\":\"2018-11-13T22:18:57+00:00\",\"dateModified\":\"2018-11-13T22:19:53+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/submission\\\/valve-using-machine-learning-and-deep-learning-to-catch-cheaters-on-csgo-794-words\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/submission\\\/valve-using-machine-learning-and-deep-learning-to-catch-cheaters-on-csgo-794-words\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/submission\\\/valve-using-machine-learning-and-deep-learning-to-catch-cheaters-on-csgo-794-words\\\/#primaryimage\",\"url\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/wp-content\\\/uploads\\\/sites\\\/4\\\/2018\\\/11\\\/CSGO.png\",\"contentUrl\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/wp-content\\\/uploads\\\/sites\\\/4\\\/2018\\\/11\\\/CSGO.png\",\"width\":464,\"height\":217},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/submission\\\/valve-using-machine-learning-and-deep-learning-to-catch-cheaters-on-csgo-794-words\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Submissions\",\"item\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/submission\\\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Valve using machine learning and deep learning to catch cheaters on CS:GO (794 words)\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/#website\",\"url\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/\",\"name\":\"Technology and Operations Management\",\"description\":\"MBA Student Perspectives\",\"potentialAction\":[{\"@type\":\"性视界Action\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Valve using machine learning and deep learning to catch cheaters on CS:GO (794 words) - Technology and Operations Management","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/valve-using-machine-learning-and-deep-learning-to-catch-cheaters-on-csgo-794-words\/","og_locale":"en_US","og_type":"article","og_title":"Valve using machine learning and deep learning to catch cheaters on CS:GO (794 words) - Technology and Operations Management","og_description":"CS:GO is one of the most popular and competitive video games worldwide. In the past few years, reports of players using &amp;amp;amp;amp;amp;quot;hacks&amp;amp;amp;amp;amp;quot; in the game were increasing, negatively impacting customer satisfaction of CS:GO's user base. To counter this rampant cheating, Valve turned to machine learning and deep learning.","og_url":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/valve-using-machine-learning-and-deep-learning-to-catch-cheaters-on-csgo-794-words\/","og_site_name":"Technology and Operations Management","article_modified_time":"2018-11-13T22:19:53+00:00","og_image":[{"width":464,"height":217,"url":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-content\/uploads\/sites\/4\/2018\/11\/CSGO.png","type":"image\/png"}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"5 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/valve-using-machine-learning-and-deep-learning-to-catch-cheaters-on-csgo-794-words\/","url":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/valve-using-machine-learning-and-deep-learning-to-catch-cheaters-on-csgo-794-words\/","name":"Valve using machine learning and deep learning to catch cheaters on CS:GO (794 words) - Technology and Operations Management","isPartOf":{"@id":"https:\/\/d3.harvard.edu\/platform-rctom\/#website"},"primaryImageOfPage":{"@id":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/valve-using-machine-learning-and-deep-learning-to-catch-cheaters-on-csgo-794-words\/#primaryimage"},"image":{"@id":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/valve-using-machine-learning-and-deep-learning-to-catch-cheaters-on-csgo-794-words\/#primaryimage"},"thumbnailUrl":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-content\/uploads\/sites\/4\/2018\/11\/CSGO.png","datePublished":"2018-11-13T22:18:57+00:00","dateModified":"2018-11-13T22:19:53+00:00","breadcrumb":{"@id":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/valve-using-machine-learning-and-deep-learning-to-catch-cheaters-on-csgo-794-words\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/d3.harvard.edu\/platform-rctom\/submission\/valve-using-machine-learning-and-deep-learning-to-catch-cheaters-on-csgo-794-words\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/valve-using-machine-learning-and-deep-learning-to-catch-cheaters-on-csgo-794-words\/#primaryimage","url":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-content\/uploads\/sites\/4\/2018\/11\/CSGO.png","contentUrl":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-content\/uploads\/sites\/4\/2018\/11\/CSGO.png","width":464,"height":217},{"@type":"BreadcrumbList","@id":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/valve-using-machine-learning-and-deep-learning-to-catch-cheaters-on-csgo-794-words\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/d3.harvard.edu\/platform-rctom\/"},{"@type":"ListItem","position":2,"name":"Submissions","item":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/"},{"@type":"ListItem","position":3,"name":"Valve using machine learning and deep learning to catch cheaters on CS:GO (794 words)"}]},{"@type":"WebSite","@id":"https:\/\/d3.harvard.edu\/platform-rctom\/#website","url":"https:\/\/d3.harvard.edu\/platform-rctom\/","name":"Technology and Operations Management","description":"MBA Student Perspectives","potentialAction":[{"@type":"性视界Action","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/d3.harvard.edu\/platform-rctom\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"}]}},"_links":{"self":[{"href":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-json\/wp\/v2\/hck-submission\/32124","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-json\/wp\/v2\/hck-submission"}],"about":[{"href":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-json\/wp\/v2\/types\/hck-submission"}],"author":[{"embeddable":true,"href":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-json\/wp\/v2\/users\/11445"}],"replies":[{"embeddable":true,"href":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-json\/wp\/v2\/comments?post=32124"}],"version-history":[{"count":0,"href":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-json\/wp\/v2\/hck-submission\/32124\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-json\/wp\/v2\/media\/32160"}],"wp:attachment":[{"href":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-json\/wp\/v2\/media?parent=32124"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-json\/wp\/v2\/categories?post=32124"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}