conftrace_

universal adversarial trigger

6 papers

Explore in graph

Also known as

UAT

Co-occurring keywords · papers mentioning both

adversarial attack (5) transformer model (2) language model (2) natural language inference (2) text classification (2) data-free approach (1) layerwise universal adversarial attack (1) hidden layer perturbation (1) gradient-guided search (1) gradient-based beam search (1)

Papers

LinkPrompt: Natural and Universal Adversarial Attacks on Prompt-based Language Models NAACL 2024 Layerwise universal adversarial attack on NLP models ACL 2023 Attack on Unfair ToS Clause Detection: A Case Study using Universal Adversarial Triggers EMNLP 2022 MINIMAL: Mining Models for Universal Adversarial Triggers AAAI 2022 Generating Label Cohesive and Well-Formed Adversarial Claims EMNLP 2020 Universal Adversarial Triggers for Attacking and Analyzing NLP EMNLP 2019