Papers by Zhixue Song

1 papers
Hard to Read, Easy to Jailbreak: How Visual Degradation Bypasses MLLM Safety Alignment (2026.findings-acl)

Copied to clipboard

Challenge: Recent advances in visual context compression enable MLLMs to process ultra-long contexts efficiently by rendering text into images.
Approach: They propose a strategy that decouples visual transcription from safety auditing by enforcing a serialized pipeline to decouple visual transcription and safety assessment.
Outcome: The proposed strategy decouples visual transcription from safety auditing to reduce the risk of jailbreaking.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations