Julia Kruk

#NeurIPS2024 is looking like the AI Hogwarts. Or is it just me?

Presenting the all-woman team behind Semi-Truths, (+ @polochau.bsky.social ) landed at #NeurIPS2024!!

🤗 Come chat with us tomorrow at 11am - 2pm, West Ballroom A-D #5211.

Learn about the weaknesses of AI-Generated Image Detectors!

NEW: CharacterAI is hosting chatbots designed to engage users in roleplay about self-harm, depicting graphic scenarios and even sharing tips for hiding self-injury from others.

The characters are widely accessible to minor users.

(TW for depictions of self-harm)

futurism.com/ai-chatbots-...

Come chat with us at NeurIPS 2024 🎉

📍 West Ballroom A-D #5211
⏰ Wednesday Dec 11th, 11 a.m. — 2 p.m. PST.

🥳 This work was an amazing collaboration between @gtresearchnews.bsky.social and @stanfordnlp.bsky.social.

🙏 Huge thank you to @judyh.bsky.social,
@polochau.bsky.social, and @diyiyang.bsky.social for their guidance!

semi-truths (Semi Truths) User profile of Semi Truths on Hugging Face

In addition to the Semi-Truths dataset, we release our pipeline to enable the community to create custom evaluation sets for their unique use cases! Please interact with our work on:

🤗HF: huggingface.co/semi-truths
👾Github: github.com/J-Kruk/SemiT...

Every image is enriched with attributes quantifying the magnitude of change achieved. Evaluating performance on these attributes provides insights into detector biases.

💡 UniversalFakeDetector suffers >35 point performance drop on different scenes, and >5 points on magnitude of change.

🔧 To control what is changed in an image and how, we use semantic segmentation datasets that provide real images, entity masks, and entity labels.

We perturb entity & image captions with LLMs, then apply different diffusion models and augmentation techniques to alter images.

🚀 We present Semi-Truths, a dataset for the targeted evaluation and training of AI-Augmented Image Detectors.

It includes a wide array of scenes & subjects, as well as various magnitudes of image augmentation. We define “magnitude” by size of the augmented region and the semantic change achieved.

An attacker may keep most of the original image, and only change a localized region to drastically change the narrative!

🔍 One such case is known as “Sleepy Joe”, where a video of Joe Biden was changed only in the facial region to make it appear as though he fell asleep at a podium.

Detecting AI-Generated images that can be used to spread misinformation is an impactful area of research in Computer Vision.

🤔 However, the majority of the SOTA systems are trained exclusively on end-to-end fully generated images, or on data from very constrained distributions.

🚨 NeurIPS 2024 🚨How robust are AI-Generated Image Detectors?

🤔 Can they detect various magnitudes of image augmentations?
💡 Does performance fluctuate across scenes?

🚀 Find out with Semi-Truths: 1.5 million images for the targeted evaluation of AI-generated images. arxiv.org/abs/2411.07472

Hi!! Would love to be added, thanks

Sharing one more for the CSS community 🦋

Huge shout out to everyone putting together these resources 🙏

If there’s still room, would love to be added! Thanks for creating this

Hi! I would love to be added! Thanks

Hi! Would love to be added - thanks so much

This is such a great resource - thanks so much for creating this!

A starter pack for #NLP #NLProc researchers! 🎉

go.bsky.app/SngwGeS

Excited to see the AI/NLP/CV communities migrating over here 🦋