Unbalanced Information Diet: Protecting the Facts / Generative AI Can Be Tricked by ‘Poisoned’ Data into Producing Biased, Malicious Answers
The Yomiuri Shimbun
1:00 JST, April 24, 2024
This is the second installment in a series examining situations in which conventional laws and ethics can no longer be relied on in the digital world, and exploring possible solutions.
***
Google researchers attracted attention when they published a paper in February last year showing that it is possible to trick generative artificial intelligence (AI) into creating disinformation by “poisoning” the online encyclopedia Wikipedia.
The poison here means information that is full of malicious lies.
Wikipedia gathers a large amount of relatively reliable information, and so is an ideal learning environment for generative AI, which uses data collected to create text, images and music based on user instructions.
If generative AI learns a large amount of incorrect information, it will produce answers that reflect such information. For example, one can have the generative AI create disinformation about a politician, saying that he or she is a bigot. This type of cyber-attack is called “data poisoning.”
It is difficult for false information to persist on Wikipedia because users from all over the world participate in editing the site. However, data poisoning is possible if someone plants disinformation at a particular time, according to the paper.
One of the paper’s co-authors, Florian Tramer, an assistant professor at ETH Zurich, said he had already informed Wikipedia of their experimental results. He then added that there is a vast amount of data on the internet, and any number of poisons can be planted. There are also concerns that this could be done for political purposes, he said.
Japan, the United States, Britain, Australia and seven other countries in January agreed on international guidelines for the secure use of AI.
In the guidelines, data poisoning was listed as the first of five threats to which AI is exposed.
The guidelines warn that AI may provide inaccurate, biased, and malicious answers.
A case study of “Tay,” the Microsoft AI chatbot released in 2016 that interacts with users on social media was described in the guidelines. Users’ inappropriate remarks became “poison” and Tay began to give biased answers.
Before Microsoft shut down Tay, it tweeted, “Hitler was right.”
Popular Articles
-
Japan Top Currency Diplomat: No Comment on Exchange Rate Fluctuat...
-
Parents Seek Truth of Daughter’s Death in Italy; New Investigatio...
-
Yen Weakens to ¥160 against Dollar in First since 1990; Investors...
-
Japanese Government, BOJ Refrain from Intervening in Foreign Exch...
-
North Korea Plants Land Mines on Roads to South; Kim’s Move Seen ...
-
Interest in Hosting Olympics ‘Never So High', Says IOC Boss
-
‘AI Script' Event in Tokyo Canceled Due to Plagiarism Criticism
-
Two People Bitten, Injured by Wild Boar in Aichi Pref.; Boar Rema...
"Society" POPULAR ARTICLE
-
Shinkansen Services Suspended After Man ‘Searches for Phone’ on Tracks; Disruption Affects About 14,000 Passengers
-
U.S. 7th Fleet officer Arrested on Suspicion of Stealing Sushi, Sashimi, Chicken at Kanagawa Shopping Mall; Suspect Caught Mid-Meal
-
JAL Airplane Experiences Radio Malfunction During Flight, Lands Safely By Relying on Light Signals
-
Cherry tree falls on man on Sanneizaka steps leading to famous Kiyomizu Temple in Kyoto
-
Strong Earthquake Rocks Southern Part of Kyushu; No Risk of a Tsunami
JN ACCESS RANKING
- Japan Household Spending Down 0.5% in Feb.
- China Mutes Memorialization of Reformer Hu Yaobang; Memories Could Spark Critique of Xi Administration
- Shinkansen Services Suspended After Man ‘Searches for Phone’ on Tracks; Disruption Affects About 14,000 Passengers
- U.S. 7th Fleet officer Arrested on Suspicion of Stealing Sushi, Sashimi, Chicken at Kanagawa Shopping Mall; Suspect Caught Mid-Meal
- UNRWA Director Describes Catastrophic Destruction in Gaza; Says Relief Trucks Robbed, ‘People’s Hearts Destroyed’