🧠 AI🟢 Bullish

Conditioned Activation Transport for T2I Safety Steering

arXiv – CS AI|Maciej Chrab\k{a}szcz, Aleksander Szymczyk, Jan Dubi\'nski, Tomasz Trzci\'nski, Franziska Boenisch, Adam Dziedzic|March 4, 2026 at 05:00 AM|1 views

🤖AI Summary

Researchers introduce Conditioned Activation Transport (CAT), a new framework to prevent text-to-image AI models from generating unsafe content while preserving image quality for legitimate prompts. The method uses a geometry-based conditioning mechanism and nonlinear transport maps, validated on Z-Image and Infinity architectures with significantly reduced attack success rates.

Key Takeaways

→Current text-to-image models remain vulnerable to generating unsafe and toxic content despite their advanced capabilities.
→Linear activation steering methods often degrade image quality when applied to benign prompts, creating a quality-safety trade-off.
→The new CAT framework uses conditioned transport maps that only activate within unsafe activation regions to minimize interference.
→SafeSteerDataset was created containing 2300 safe and unsafe prompt pairs to support the research.
→Testing on Z-Image and Infinity architectures showed CAT effectively reduces attack success rates while maintaining image fidelity.

#ai-safety #text-to-image #content-moderation #machine-learning #image-generation #safety-steering #research #arxiv

Read Original →via arXiv – CS AI

Act on this with AI

Stay ahead of the market.

Connect your wallet to an AI agent. It reads balances, proposes swaps and bridges across 15 chains — you keep full control of your keys.

Connect Wallet to AI →How it works

AI1h ago

Warren Buffett complained for decades that boosting profits by excluding exec stock comp was ‘cynical’—Nvidia just surprised Wall Street and agreed

Nvidia surprised Wall Street by agreeing to include executive stock compensation in its profit calculations, addressing a decades-old complaint by Warren Buffett about excluding such costs. This accounting change will likely boost Nvidia's credibility with investors while potentially pressuring competitors to follow suit.

AI4h ago

A Neuropsychologically Grounded Evaluation of LLM Cognitive Abilities

Researchers introduced NeuroCognition, a new benchmark for evaluating LLMs based on neuropsychological tests, revealing that while models show unified capability across tasks, they struggle with foundational cognitive abilities. The study found LLMs perform well on text but degrade with images and complexity, suggesting current models lack core adaptive cognition compared to human intelligence.

AI4h ago

Estimating Visual Attribute Effects in Advertising from Observational Data: A Deepfake-Informed Double Machine Learning Approach

Researchers developed DICE-DML, a new framework that uses deepfake technology and machine learning to measure causal effects of visual attributes in digital advertising. The method addresses bias issues in standard approaches when analyzing how image elements like skin tone affect consumer engagement on social media platforms.