conftrace_

textual backdoor

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

backdoor attack (2) online defense (1) feature-based detection (1) attack invisibility (1) distance-based score (1) feature-level defense (1) distance-based anomaly score (1) neural network (1) word substitution (1) adversarial attack (1)

Papers

Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks EMNLP 2022 Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution ACL 2021