#vlm-vulnerabilities News & Analysis

2 articles tagged with #vlm-vulnerabilities. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

2 articles

AIBearisharXiv – CS AI · May 287/10

🧠

MIRAGE: Context-Aware Prompt Injection against Mobile GUI Agents via User-Generated Content

Researchers demonstrate MIRAGE, a technique that exploits vision-language model vulnerabilities in mobile GUI agents by injecting adversarial text into user-generated content regions. The attack achieves 23-30% success rates across five VLM agents without modifying apps or operating systems, revealing a critical security gap in AI-powered mobile automation that existing visual-quality defenses cannot reliably prevent.

AIBearisharXiv – CS AI · May 17/10

🧠

The Effects of Visual Priming on Cooperative Behavior in Vision-Language Models

Researchers demonstrate that Vision-Language Models (VLMs) can be influenced by visual priming through images and color cues in decision-making tasks, raising concerns about their reliability in safety-critical applications. The study uses the Iterated Prisoner's Dilemma framework to test whether exposure to behavioral concepts and visual cues alters cooperative behavior, finding varying susceptibility across different models and proposing mitigation strategies.