This work has been submitted to the IEEE for possible publication. Abstract Face swapping manipulations in video streams represents an increasing threat in remote video communications, due to advances in automated and real-time tools. Recent literature proposes to characterize and exploit visual artifacts introduced in video frames by swapping algorithms when dealing with challenging physical scenes, such as face occlusions. This paper investigates the effectiveness of this approach by benchmarking CNN-based data-driven models on two data corpora (including a newly collected one) and analyzing generalization capabilities with respect to different acquisition sources and swapping algorithms. The results confirm excellent performance of general-purpose CNN architectures when operating within the same data source, but a significant difficulty in robustly characterizing occlusion-based visual cues across datasets. This highlights the need for specialized detection strategies to deal with such artifacts. The synthesis and manipulation of facial images and videos have achieved increasingly hyper-realistic results in recent years [4], leading to numerous research efforts for the automated identification of non-genuine visual data [25] [27].

We're gearing up to cover Apple's Worldwide Developers Conference (WWDC) next week! In this episode, Cherlynn and Devindra dive into everything they expect at WWDC: Tons of AI announcements; more on iOS 18, iPadOS 18, and macOS 15; and hopefully some improvements for Vision Pro and visionOS. In addition, we chat about what we expect to see at Summer Game Fest and demonstrate how we used an AI editing tool to clear up some awful podcast audio. Devindra also talks with Justin Samuels, the founder of Render ATL, about why he started a massive tech conference in Atlanta. Listen below or subscribe on your podcast app of choice. If you've got suggestions or topics you'd like covered on the show, be sure to email us or drop a note in the comments! And be sure to check out our other podcast, Engadget News! Humane AI warns users its battery case "may pose a fire risk" – 34:36 Welcome back to the Engadget podcast. This week we are getting ready for WWDC 2024 happening in a couple of days.

Microsoft made some unusually major moves ahead of its Build developer conference: It announced a new Copilot initiative for powerful AI PCs, which will be led by the new Surface Pro and Surface Laptop. These machines are powered by Qualcomm's new Snapdragon X Plus and Elite chips, and they come with a special version of Windows 11 optimized for Arm mobile chips and AI. Basically, Microsoft is doing for PCs what Apple did with its M-series Macs four years ago. We still don't know how well these new machines will perform, but it sounds like Microsoft has certainly heard our complaints about Arm-based Windows devices. Listen below or subscribe on your podcast app of choice. If you've got suggestions or topics you'd like covered on the show, be sure to email us or drop a note in the comments! And be sure to check out our other podcast, Engadget News! Devindra: Hey everyone, this is Devindra here. I had a chance to chat with Pavan Davuluri, the head of Microsoft Windows and Devices, basically the team in charge of Surface and Windows. And we talked about the new Copilot Plus Surface PCs, the Surface Pro and the Surface Laptop, and the whole new Copilot Plus initiative in general. We've reviewed quite a few of the ARM based Windows PCs and you know, they have not worked out so well. So I think this could be different, at least from the benchmarks we've seen.

Recent text-based causal methods attempt to mitigate confounding bias by including unstructured text data as proxies of confounding variables that are partially or imperfectly measured. These approaches assume analysts have supervised labels of the confounders given text for a subset of instances, a constraint that is not always feasible due to data privacy or cost. Here, we address settings in which an important confounding variable is completely unobserved. We propose a new causal inference method that splits pre-treatment text data, infers two proxies from two zero-shot models on the separate splits, and applies these proxies in the proximal g-formula. We prove that our text-based proxy method satisfies identification conditions required by the proximal g-formula while other seemingly reasonable proposals do not. We evaluate our method in synthetic and semi-synthetic settings and find that it produces estimates with low bias. This combination of proximal causal inference and zero-shot classifiers is novel (to our knowledge) and expands the set of text-specific causal methods available to practitioners.

New research from New York University adds to the growing indications that we may soon have to take the deepfake equivalent of a'drunk test' in order to authenticate ourselves, before commencing a sensitive video call – such as a work-related videoconference, or any other sensitive scenario that may attract fraudsters using real-time deepfake streaming software. Some of the active and passive challenges applied to video-call scenarios in GOTCHA. The user must comply with and pass the challenges, while additional'passive' methods (such as attempting to overload a potential deepfake system) are used over which the participant has no influence. The proposed system is titled GOTCHA – a tribute to the CAPTCHA systems that have become an increasing obstacle to web-browsing over the last 10-15 years, wherein automated systems require the user to perform tasks that machines are bad at, such as identifying animals or deciphering garbled text (and, ironically, these challenges often turn the user into a free AMT-style outsourced annotator). In essence, GOTCHA extends the August 2022 DF-Captcha paper from Ben-Gurion University, which was the first to propose making the person at the other end of the call jump through a few visually semantic hoops in order to prove their authenticity.

Maintainers are preparing to release pip 20.3, with the new resolver on by default. Confusion and curiosity struck their hearts! They asked themselves: What is this new resolver? How can I learn more? Did I leave the oven on?

When it comes to an AI (Artificial Intelligence) project, there is usually lots of excitement. The focus is often on using new-fangled algorithms – such as deep learning neural networks – to unlock insights that will transform the business. But in this process, something often gets lost: The importance of establishing the right plan for the data. Keep in mind that 80% of the time of an AI project can be spent on identifying, storing, processing and cleansing data. "The big gotcha is having bad data fed into your AI systems," said David Linthicum, who is the Chief Cloud Strategy Officer at Deloitte Consulting LLP.

When it comes to an AI (Artificial Intelligence) project, there is usually lots of excitement.

AI-related deep learning and machine learning techniques have become a common area of discussion in big data circles. The trend is something for data managers to keep an eye on for a number of reasons, not the least of which is the new technologies' potential effect on modern data infrastructure. Increasingly at the center of the discussion is the graphics processor unit (GPU). It has become an established figure on the AI landscape. GPU deep learning has been bubbling under the surface for some time, but the pace of development is quickening.

Early last year, a man walked into a hardware store in Oregon, picked up a basket, and began placing a number of expensive items into it. At first glance, that alone would not have been enough to raise suspicion. However, before finishing the purchase process at a self-service kiosk, the man picked up his items and abruptly left the store. Fortunately for the retailer, the checkout kiosk had a camera that captured a photo of the thief. Unfortunately for the thief, the Washington County Sheriff's Office assigned to investigate the case had recently implemented a facial recognition system that was able to match the kiosk photo with a database containing more than 300,000 images.