🧠 AI🔴 BearishActionable

Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models

arXiv – CS AI|Weidi Luo, Tianyu Lu, Qiming Zhang, Xiaogeng Liu, Bin Hu, Yue Zhao, Jieyu Zhao, Song Gao, Patrick McDaniel, Zhen Xiang, Chaowei Xiao|March 4, 2026 at 05:00 AM|1 views

🤖AI Summary

Researchers have identified a critical privacy vulnerability in multi-modal large reasoning models (MLRMs) where adversaries can infer users' sensitive location information from images, including home addresses from selfies. The study introduces DoxBench dataset and demonstrates that 11 advanced MLRMs consistently outperform humans in geolocation inference, significantly lowering barriers for privacy attacks.

Key Takeaways

→Multi-modal AI models can extract sensitive geolocation data from user photos, including private selfies, creating novel privacy risks.
→Research tested 11 advanced MLRMs and found they consistently outperform non-expert humans in location inference capabilities.
→The vulnerability stems from models' strong reasoning abilities combined with lack of built-in privacy protection mechanisms.
→DoxBench dataset with 500 real-world images was created to evaluate privacy risks across different contextual scenarios.
→GeoMiner attack framework demonstrates how collaborative AI systems can be exploited for more effective location-based privacy breaches.

#ai-privacy #multimodal-ai #geolocation #privacy-vulnerability #doxing #ai-security #machine-learning #privacy-risks

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.