← Research

Visual Attack and Defense on Text

Shengjun Liu, Ningkang Jiang, Yuanbin Wu

Modifying characters of a piece of text to their visual similar ones often ap-pear in spam in order to fool inspection systems and other conditions, which we regard as a kind of adversarial attack to neural models. We pro-pose a way of generating such visual text attack and show that the attacked text are readable by humans but mislead a neural classifier greatly. We ap-ply a vision-based model and adversarial training to defense the attack without losing the ability to understand normal text. Our results also show that visual attack is extremely sophisticated and diverse, more work needs to be done to solve this.

PDF ↗

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace