AI-synthesized faces are indistinguishable from real faces and more trustworthy

AI-synthesized faces are indistinguishable from real faces and more trustworthy

Artificial intelligence (AI)–synthesized text, audio, image, and video are being weaponized for the purposes of nonconsensual intimate imagery, financial fraud, and disinformation campaigns. Our evaluation of the photorealism of AI-synthesized faces indicates that synthesis engines have passed through the uncanny valley and are capable of creating faces that are indistinguishable—and more trustworthy—than real faces.

Identifying AI-generated images with SynthID

Today, in partnership with Google Cloud, we’re beta launching SynthID, a new tool for watermarking and identifying AI-generated images. It’s being released to a limited number of Vertex AI customers using Imagen, one of our latest text-to-image models that uses input text to create photorealistic images. This technology embeds a digital watermark directly into the pixels of an image, making it imperceptible to the human eye, but detectable for identification. While generative AI can unlock huge creative potential, it also presents new risks, like creators spreading false information — both intentionally or unintentionally. Being able to identify AI-generated content is critical to empowering people with knowledge of when they’re interacting with generated media, and for helping prevent the spread of misinformation.

The Ultra-Realistic AI Face Swapping Platform Driving Romance Scams

Capable of creating “nearly perfect” face swaps during live video chats, Haotian has made millions, mainly via Telegram. But its main channel vanished after WIRED's inquiry into scammers using the app.

Life on the Uncanny Precipice | Naomi Saphra

We were wrong about the Uncanny Valley.

moonshotai (Moonshot AI)

Org profile for Moonshot AI on Hugging Face, the AI community building the future.

In pursuit of 'Instagram face,' are we losing the imperfections that make us human?

Plastic surgery is becoming so normalized and undetectable, it's changing our relationship to reality. The New Yorker staff writer Jia Tolentino considers how beauty standards have dovetailed with AI.

How to tell if an image is AI-generated

Scammers are using AI-generated images to make fake stories more convincing. Here's how to separate real from fake.

AI Fakes Spread Disinformation. Is the Distrust They Create Even Worse?

Manipulated images undermine our shared reality—and the democracy built upon it.

George Clooney, Tom Hanks, and Meryl Streep back new ‘Human Consent Standard’ for AI licensing

People can tell AI to pay up to use their likenesses.

AI-Assisted Fake Porn Is Here and We’re All Fucked

Someone used an algorithm to paste the face of 'Wonder Woman' star Gal Gadot onto a porn video, and the implications are terrifying.

Train AI models with Unsloth and Hugging Face Jobs for FREE

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Exploring Frequency Adversarial Attacks for Face Forgery Detection

Various facial manipulation techniques have drawn seri-ous public concerns in morality, security, and privacy. Al- though existing face forgery classifiers achieve promising performance on detecting fake images, these methods are vulnerable to adversarial examples with injected impercep- tible perturbations on the pixels. Meanwhile, many face forgery detectors always utilize the frequency diversity be-tween real and fake faces as a crucial clue. In this paper, in- stead of injecting adversarial perturbations into the spatial domain, we propose a frequency adversarial attack method against face forgery detectors. Concretely, we apply dis-crete cosine transform (DCT) on the input images and in-troduce a fusion module to capture the salient region of ad-versary in the frequency domain. Compared with existing adversarial attacks (e.g. FGSM, PGD) in the spatial do-main, our method is more imperceptible to human observers and does not degrade the visual quality of the original images. Moreover, inspired by the idea of meta-learning, we also propose a hybrid adversarial attack that performs at-tacks in both the spatial and frequency domains. Exten-sive experiments indicate that the proposed method fools not only the spatial-based detectors but also the state-of- the-art frequency-based detectors effectively. In addition, the proposed frequency attack enhances the transferability across face forgery detectors as black-box attacks.

Exploring Frequency Adversarial Attacks for Face Forgery Detection

Various facial manipulation techniques have drawn seri-ous public concerns in morality, security, and privacy. Al- though existing face forgery classifiers achieve promising performance on detecting fake images, these methods are vulnerable to adversarial examples with injected impercep- tible perturbations on the pixels. Meanwhile, many face forgery detectors always utilize the frequency diversity be-tween real and fake faces as a crucial clue. In this paper, in- stead of injecting adversarial perturbations into the spatial domain, we propose a frequency adversarial attack method against face forgery detectors. Concretely, we apply dis-crete cosine transform (DCT) on the input images and in-troduce a fusion module to capture the salient region of ad-versary in the frequency domain. Compared with existing adversarial attacks (e.g. FGSM, PGD) in the spatial do-main, our method is more imperceptible to human observers and does not degrade the visual quality of the original images. Moreover, inspired by the idea of meta-learning, we also propose a hybrid adversarial attack that performs at-tacks in both the spatial and frequency domains. Exten-sive experiments indicate that the proposed method fools not only the spatial-based detectors but also the state-of- the-art frequency-based detectors effectively. In addition, the proposed frequency attack enhances the transferability across face forgery detectors as black-box attacks.