Blurry Images Create a ‘Comfort Zone’ for Jailbreaking Multimodal LLMs

A new study from Westlake University shows that when harmful text is rendered as low‑resolution, blurry, or noisy images, multimodal large language models become significantly easier to jailbreak despite still recognizing the text, revealing a U‑shaped risk curve and a simple mitigation that decouples OCR from safety checks.

OCRjailbreakmultimodal LLM

0 likes · 10 min read

Blurry Images Create a ‘Comfort Zone’ for Jailbreaking Multimodal LLMs

Machine Heart

Jun 14, 2026 · Artificial Intelligence

When Blurry Images Create an Attack Comfort Zone for Multimodal LLMs

Westlake University's AGI Lab shows that when harmful text is rendered as low‑resolution, blurry or noisy images, multimodal large language models can still read the content but their safety filters fail, creating an 'attack comfort zone' that dramatically raises jailbreak success rates across several models.

OCRjailbreakmultimodal LLM

0 likes · 9 min read

When Blurry Images Create an Attack Comfort Zone for Multimodal LLMs

Xiaomi Tech

Mar 3, 2026 · Artificial Intelligence

Xiaomi Scores 14 Papers at CVPR 2026, Showcasing Breakthroughs in Large Models and Autonomous Driving

CVPR 2026 accepted 14 Xiaomi papers spanning long‑video understanding, multimodal reasoning, GUI agents, and autonomous driving, each accompanied by arXiv and GitHub links, and introducing novel frameworks such as REVISOR, EMO‑R3, TimeViper, MSJoE, SafeGRPO, GUI‑CEval, ProactiveMobile, ParkGaussian, UFO, TraqPoint, SimScale, MeanFuser and DVGT.

Autonomous DrivingCVPR 2026Long Video Understanding

0 likes · 19 min read

Xiaomi Scores 14 Papers at CVPR 2026, Showcasing Breakthroughs in Large Models and Autonomous Driving

AIWalker

Jun 18, 2025 · Artificial Intelligence

Six New Directions for Large Language Models

Large language models are booming, and this article highlights six cutting‑edge research directions—LLM‑plus synthetic data, reward modeling, inference techniques, LLM‑as‑a‑Judge, safety alignment, and long‑context handling—each illustrated with recent papers, experimental results, and links to code repositories.

LLMReward ModelingSynthetic Data

0 likes · 9 min read

Six New Directions for Large Language Models