Intel Claims 96% Accuracy In Detecting Deepfake

November 18, 2022 By Monica Green

(Image Credit Google)

Deepfake technology, in which someone's likeness is digitally superimposed on someone else's, has some very sinister implications. Intel claims that its new deepfake detection technology, FakeCatcher, can detect a deepfake video 96% of the time. Intel announced that FakeCatcher can detect deepfake videos in real-time and that it is the first of its kind in the world. FakeCatcher reportedly detects fake likenesses with a 96% success rate and collects data on subtle blood flow mechanics on a person's face by scanning the pixels in a video. Then, a deep learning AI can determine whether or not the subject's likeness is genuine. FakeCatcher was created using Intel technology by Intel researchers Ilke Demir and Umur Ciftci from the State University of New York at Binghamton. [caption id="attachment_63888" align="aligncenter" width="1200"] Intel

Image credit: candid[/caption] “Deepfake videos are everywhere now. You have probably already seen them; videos of celebrities doing or saying things they never actually did,” says Intel Labs senior staff researcher Ilke Demir in an Intel press release. FakeCatcher runs on a server but communicates with videos via a web-based platform. According to Intel, the technology's approach is diametrically opposed to traditional deep-learning-based detectors, which typically seek out what's fake about a video, whereas FakeCatcher seeks out what's real. [caption id="attachment_63889" align="aligncenter" width="1200"]

Image credit: rappler[/caption] Demir explained to VentureBeat that FakeCatcher's approach is based on photoplethysmography (PPG), a method for determining changes in blood flow in human tissue. When a real person appears on screen, their tissue changes color very slightly microscopically as blood flows through their veins. This change in complexion cannot be replicated by deepfakes (at least not yet). Deepfake technology appears to have advanced in recent years. The FBI reported to its Internet Crime Complaint Center this summer that it had received an increase in complaints about people using deepfakes to apply for remote jobs, with a focus on voice spoofing. Binance CCO Patrick Hillman stated in a blog post in August that hackers were impersonating him in meetings by copying his digital likeness.

By Monica Green

I am specialised in latest tech and tech discoveries.

Intel Claims 96% Accuracy In Detecting Deepfake

Walmart's GenAI Search Engine: Challenging Google's Dominance in Retail Search

Introducing the MSI Claw Handheld: Your Ultimate Gaming Companion

Uber Increases In-App Ads, Prompting Mixed Reactions from Customers

Apple's iOS 18: A Leap into the AI Era

Google's Regular Pixel 8 Won't Get Gemini Nano AI

MacBook Air M3 Makes Amends for M2's Storage Blunder

Samsung Unveils the Galaxy M15 5G

Elon Musk's xAI to Open-Source Chatbot Grok

Contra: Operation Galuga - A Modern Run-and-Gun Classic

Musk Confirms X's TV App Arrives This Week

Tech Titan Elon Musk Unveils XMail, Challenging Gmail's Dominance

WhatsApp Stories Get a Makeover: Easier to Catch Up with Friends' Updates!

Cash App Heats Savings Game with 4.5% APY, But Watch the Catches!

Shazam Gets Mind-Reading Headphones?

Artisse AI raises $6.7 million for its 'more realistic' AI photography app.

How to search the web with ChatGPT?