Adversarial Text Attacks

Adversarial text attacks study how changes to wording, spelling, typography, style, or prompt structure can alter a model’s predictions or bypass safeguards. Common approaches include synonym and character substitutions, paraphrasing and style rewriting, black-box search guided by model feedback, and adversarial suffixes; defenses include adversarial training, input normalization, detection, and certified robustness methods. Evaluations span text classification, content moderation, AI-generated-text detection, retrieval and ranking, and LLM safety, with growing attention to multilingual and multimodal settings. A central challenge is making attacks effective while preserving meaning and readability, and ensuring that defenses generalize to adaptive attacks without rejecting benign inputs.