iiinova — where your digital self keeps evolving

Julia Kruk @juliakruk.bsky.social · 12/12/2024

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

Julia Kruk @juliakruk.bsky.social · 11/12/2024

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!

0101 0

Reposted by Julia Kruk

Maggie Harrison Dupré @mharrisondupre.bsky.social · 07/12/2024

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-...

67443 0

Julia Kruk @juliakruk.bsky.social · 05/12/2024

Come chat with us at NeurIPS 2024 🎉 📍 West Ballroom A-D #5211 ⏰ Wednesday Dec 11th, 11 a.m. — 2 p.m. PST.

000 0

Julia Kruk @juliakruk.bsky.social · 05/12/2024

🥳 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!

120 0

Julia Kruk @juliakruk.bsky.social · 05/12/2024

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...

huggingface.co

semi-truths (Semi Truths)

User profile of Semi Truths on Hugging Face

100 0

Julia Kruk @juliakruk.bsky.social · 05/12/2024

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.

100 0

Julia Kruk @juliakruk.bsky.social · 05/12/2024

🔧 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.

100 0

Julia Kruk @juliakruk.bsky.social · 05/12/2024

🚀 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.

100 0

Julia Kruk @juliakruk.bsky.social · 05/12/2024

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.

100 0

Julia Kruk @juliakruk.bsky.social · 05/12/2024

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.

100 0

Julia Kruk @juliakruk.bsky.social · 05/12/2024

🚨 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