Skip to content
conftrace_

adversarial text detection

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

text classification (3) adversarial attack detection (2) adversarial text (2) prediction correction (1) perturbed word detection (1) hard label voting (1) embedding sensitivity (1) perturbation identification (1) text transformation (1) hard label (1)

Papers

Guided Perturbation Sensitivity (GPS): Detecting Adversarial Text via Embedding Stability and Word Importance AAAI 2026 VoteTRANS: Detecting Adversarial Text without Training by Voting on Hard Labels of Transformations ACL 2023 CheckHARD: Checking Hard Labels for Adversarial Text Detection, Prediction Correction, and Perturbed Word Suggestion EMNLP 2022 Detecting Word-Level Adversarial Text Attacks via SHapley Additive exPlanations ACL 2022