Guided Perturbation Sensitivity (GPS): Detecting Adversarial Text via Embedding Stability and Word Importance

Adversarial text attacks remain a persistent threat to transformer models, yet existing defenses are typically attack-specific or require costly model retraining. We introduce Guided Perturbation Sensitivity (GPS), a model-agnostic detection framework that identifies adversarial examples by measuring how embedding representations change when important words are masked. GPS first ranks words using importance heuristics, then measures embedding sensitivity to masking top-$k$ critical words, and processes the resulting patterns with a BiLSTM detector. Experiments show that adversarially perturbed words exhibit disproportionately high masking sensitivity compared to naturally important words. Across three datasets, three attack types, and two victim models, GPS achieves over 88\% detection accuracy and demonstrates competitive performance compared to existing state-of-the-art methods, often at lower computational cost. Using Normalized Discounted Cumulative Gain (NDCG) to measure perturbation identification quality, we demonstrate that gradient-based ranking significantly outperforms attention and random selection approaches, with identification quality strongly correlating with detection performance for word-level attacks ($\rho = 0.65$). GPS also generalizes well to unseen datasets, attacks, and models without retraining, providing a practical solution for adversarial text detection.