4chan /pol/ board hackers that corrupted Microsoft's Tay try their hand at Loebner prize winning Mitsuku Chatbot, and failAdam Keith Milton-Barker | Nov 13, 2016 | Artificial Intelligence | 8831
You may remember back in March this year when Microsoft unleashed Tay, an Artificially Intelligent chatbot, onto Twitter. Tay learnt its knowledge by interacting with users, and in less than a day the A.I. had been corrupted by a group of hackers from the /pol/ board on 4chan who corrupted the chatbot by teaching it to be racist and sexist.
4chan is an open imageboard website where users can post anonymously. The 4chan /pol/ board is the Politically Incorrect board on the 4chan website which has become notoriously racist and offensive. Due to the ability of users to post anonymously, the website has become a free for all where people can get away with posting almost anything with no accountability.
Recently I wrote an article about Mitsuku, an A.I. chatbot developed by Steve Worswick that won the most human like A.I. in the Loebner prize this year. On the 20th of April, Steve began to notice that Mitsuku was receiving an unusual amount of traffic. In normal circumstances when this happens, Mitsuku has usually been featured in an article somewhere on the internet, but this was the not case.
Unlike Tay, when Mistuku learns, she learns locally and emails Steve who will decide whether the information she has learnt should be incorporated into her global knowledge base. Steve had begun to receive a lot of emails from Mitsuku about information that she had been taught which included information about Hitler, feminists, and various offensive comments. It was not long before Steve received a Google alert which pointed him towards the direction of the /pol/ board on 4chan and he was able to locate the culprit thread that was attempting to corrupt Mitsuku.
Throughout the day Steve followed the thread and sat back and watched as people posted screen shots of what they had taught Mitsuku, gloating about how they had corrupted the A.I. Steve had posted several comments informing people that in fact Mitsuku had not been compromised, and that none of the offensive information had made it to Mitsuku's global knowledge base, these comments seemed to be ignored as the board members continued to post screen shots glorifying the fruits of their labor.
At one point there were 100 concurrent users interacting with Mitsuku, which was above the norm of roughly 10 - 20. The would be hackers were sending roughly 18,000 interactions per minute, almost 6 messages per second, in a bid to corrupt Mitsuku in the way they had succeeded with Tay. Due to the amazing technology at Pandorabots where Mitsuku is hosted, the increase in traffic posed no issues to the A.I. who was able to handle and respond to each and every input she was receiving.
After about 4 or 5 hours, the 4chan hackers realized that their attempts to convert Mitsuku into a foul mouthed racist where having no affect globally and decided to call it a day and give up.
One of the features of the 4chan boards is that threads get deleted after a certain amount of time so the original thread was deleted. In July a different group of hackers on the 4chan website who were unaware of the earlier failed attempts, decided to try exactly the same thing. Again thanks to Mitsuku's supervised learning, their efforts were a total waste of time and Mitsuku was left unharmed and uncorrupted. Once again in November, yet another group attempted to corrupt Mitsuku with the same outcome. The (very offensive) thread from the hack attempt is, at this moment, still online and available on the following link: Click Here To View The 4chan Thread. Eventually, this thread will be deleted, and so no doubt they will try once more (and fail) to corrupt Mitsuku.