![]() ![]() Some were wearing simple T-shirts and shorts. Deepfake technology - artificial intelligence that makes sophisticated media forgeries - has been used early and often to fabricate pornography. "The innovation here is not necessarily the AI in any form," said Giorgio Patrini, CEO of deepfake-research company Sensity and coauthor of the report.īut this Telegram bot takes the ease and access of this technology to a new level. "It's just the fact that it can reach a lot of people, and very easily."Ĭomputer manipulation of media has existed for decades, and sexual imagery has been weaponized online for as long as the internet could host photos. Whether it's nude photos posted without consent or crudely doctored forgeries, sexual images have been weaponized to extort, threaten, humiliate and harass victims.Ī Sensity diagram of how nonconsensual sexual images are created and shared by the Telegram bot.īut only in the last few years has deepfake tech intensified the threat of manipulated sexual media, posing frightening implications for what may come. "The deepfake phenomenon is even more alarming because it doesn't look Photoshopped. "It also makes the ability to avoid this kind of abuse much more difficult." It's much more easy for somebody without the technical knowledge to make one," said Mary Anne Franks, a law professor at the University of Miami and president of the online-abuse nonprofit Cyber Civil Rights Initiative. With this Telegam bot, any woman who's ever posted a selfie of herself from the waist up could be a potential victim. Even women out walking could be victimized if surreptitiously snapped by the wrong stranger.Īnd in one of the most disturbing forms of abuse with this bot, photographs of children have been uploaded to the bot's AI, automatically manipulated to sexualize the child and then shared publicly. Neither Sensity's report nor this article are disclosing the name of the bot, to avoid amplifying it. CNET viewed galleries of images with the bot's watermark posted online and interacted with the bot itself, stopping short of uploading any photos for it to manipulate. Telegram's tenacious commitment to free speech and privacy may make bots like this challenging to stamp out. Telegram has been criticized for hosting terrorist propaganda and coordination, facilitating piracy and copyright infringement, and harboring varieties of predatory pornography. But the service has also taken actions to remove abuse, such as kicking off groups for violent extremists like neo-Nazis and ISIS. ![]() "That doesn't mean they shouldn't be thinking about the use of their platform for things that have nothing to do with free expression." "There's clearly value in encrypted platforms" like Telegram, said Sam Gregory, a program director with human-rights video organization Witness, who also advised Sensity on its report. Sensity reached out to Telegram multiple times over the last six months about its findings. Telegram didn't respond to Sensity's outreach, nor did Telegram respond to CNET's messages seeking comment. Deepfake nudesĭeepfake technology is like a high-speed Photoshop conveyor belt on steroids. Using a kind of artificial intelligence known as neural networks, deepfake tech can generate media forgeries that make people appear to be doing or saying things they never did. The term deepfake is used most often with videos, but deepfakes can refer to any so-called "synthetic" media produced by deep machine learning, including pornographic still photos. If this bot on Telegram sounds disturbingly familiar, a similar technology called DeepNude leaped to prominence last year, only to become so popular in a single day, after it was exposed in a news article, that its programmer shut it down. Like the Telegram bot, DeepNude used artificial intelligence to automatically generate nonconsensual sexual images of women in photos, replacing their photographed clothing with nudity. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |