Presearch's "Doppelgänger" is trying to help people discover adult creators rather than use nonconsensual deepfakes. For three days in February, porn star Alix Lynx flew to Miami for her first exclusive creator gathering where she was in full grind mode: shooting Reels and talking strategy with other creators. "It was kind of like SoHo House for OnlyFans girls," she says of the experience, which is called The Circle and drew more than a dozen sex workers, including Remy LaCroix and Forrest Smith. Lynx, who is a former webcam model turned OnlyFans starlet, has a combined 2 million followers across Instagram, TikTok, and X . She joined OnlyFans in 2017 with "the luxury of having my own following," she says, but those numbers haven't always translated to subscriptions. It's why she was in Miami.

Digital clones--AI models that replicate a specific person--package together a few technologies that have been around for a while now: hyperrealistic video models to match your appearance, lifelike voices based on just a couple of minutes of speech recordings, and conversational chatbots increasingly capable of holding our attention. But they're also offering something the ChatGPTs of the world cannot: an AI that's not smart in the general sense, but that'thinks' like you do. Could well-crafted clones serve as our stand-ins? I certainly feel stretched thin at work sometimes, wishing I could be in two places at once, and I bet you do too. To find out, I tried making a clone of myself.

Many machine learning (ML) classifiers are claimed to outperform humans, but they still make mistakes that humans do not. The most notorious examples of such mistakes are adversarial visual metamers. This paper aims to define and investigate the phenomenon of adversarial Doppelgangers (AD), which includes adversarial visual metamers, and to compare the performance and robustness of ML classifiers to human performance. We find that AD are inputs that are close to each other with respect to a perceptual metric defined in this paper. AD are qualitatively different from the usual adversarial examples. The vast majority of classifiers are vulnerable to AD and robustness-accuracy trade-offs may not improve them. Some classification problems may not admit any AD robust classifiers because the underlying classes are ambiguous. We provide criteria that can be used to determine whether a classification problem is well defined or not; describe the structure and attributes of an AD-robust classifier; introduce and explore the notions of conceptual entropy and regions of conceptual ambiguity for classifiers that are vulnerable to AD attacks, along with methods to bound the AD fooling rate of an attack. We define the notion of classifiers that exhibit hypersensitive behavior, that is, classifiers whose only mistakes are adversarial Doppelgangers. Improving the AD robustness of hyper-sensitive classifiers is equivalent to improving accuracy. We identify conditions guaranteeing that all classifiers with sufficiently high accuracy are hyper-sensitive. Our findings are aimed at significant improvements in the reliability and security of machine learning systems.

When working with data produced by sensors recording machinery events, large datasets including hundreds or thousands of variables are usual. In these cases, many variables can be candidates to predict some target measures. However, especially in industrial contexts, data can include fully linearly dependent or very correlated variables. For example, a sensor can extract several features from the same process as linear transformations of the same basis (like the sum of a set of records, their mean, etc.). In other cases, there are genuinely different measures but related by nature, or representing two opposite facets of the same phenomenon (imagine two complementary elements of a chemical mixture).

Back in 2018, the Google Arts & Culture app introduced a feature that looks your doppelgänger in works of art. It's searched for matches for more than 120 million selfies so far. Now, the app can look for animals in art that resemble your pets too. Using a machine learning algorithm, Pet Portraits matches a snap of your furry, finned or feathered friend against tens of thousands of works from Google's partner institutions. The app might determine that the best match for your pet is in a piece of street art from Mexico or a cat figurine from ancient Egypt.

Within 10 minutes of its birth, a baby fawn is able to stand. Within seven hours, it is able to walk. Between those two milestones, it engages in a highly adorable, highly frenetic flailing of limbs to figure it all out. While autonomous robots, like self-driving cars, are already a familiar concept, autonomously learning robots are still just an aspiration. Existing reinforcement-learning algorithms that allow robots to learn movements through trial and error still rely heavily on human intervention.

Last year, graphics processing chip manufacturer NVIDIA released a new AI platform for video calls. The AI platform, Maxine, offers several intriguing features, including the game-changing ability to make it look like you're paying attention when you're not. Now, NVIDIA scientists have come up with another video-conferencing AI; one that'll let people use what are essentially deepfake versions of themselves for calls. The company's obviously building out Maxine, and looking for ways to make video conferencing better in general. The purpose of this particular AI is to lessen the amount of information that needs to be transmitted through the network in order to have clear video calls.

Deep within the encrypted bowels of the dark Web, beyond the reach of regular search engines, hackers and cybercriminals are brazenly trading a new breed of digital fakes. Yet unlike AI-generated deepfake audio and video--which embarrass the likes of politicians and celebrities by making them appear to say or do things they never would--this new breed of imitators is aimed squarely at relieving us of our hard-earned cash. Comprising highly detailed fake user profiles known as digital doppelgängers, these entities convincingly mimic numerous facets of our digital device IDs, alongside many of our tell-tale online behaviors when conducting transactions and e-shopping. The result: credit card fraudsters can use these doppelgängers to attempt to evade the machine-learning-based anomaly-detecting antifraud measures upon which banks and payments service providers have come to rely. It is proving to be big criminal business: many tens of thousands of doppelgängers are now being sold on the dark Web.

I recently read an article that had me asking, "Is it going to be fashionable to tap into the digital afterlife of an ex-employee?". The write-up referenced a report that stated; for a large organisation, it can take an average of 28 weeks for new workers to reach optimum productivity level. So, therefore, losing an employee can come at a cost. The solution could be for companies to use a kind of technology that would help their new recruits get up to speed via an ex-employee's digital doppelgänger. With costs estimated to be around £30,614 to replace a departing employee, the primary challenge is transferring the knowledge that the ex-employee accumulated in their role at the company to a new, greener employee.

If you've ever wondered if there's a museum portrait somewhere that looks like you and you're ready to have your ego crushed, there's now an app for that. Google Arts & Culture's latest update now lets you take a selfie, and using image recognition, finds someone in its vast art collection that most resembles you. It will then present you and your fine art twin side-by-side, along with a percentage match, and let you share the results on social media, if you dare. The app is like an automated version of an article that circulated recently showing folks standing in front of portraits at museums. In many cases, the old-timey people in the paintings resemble them uncannily, but, other than in rare cases, that's not the case at all with Google's app.