All Papers

0 / 0 papers shown

Title

Don't Retrain, Just Rewrite: Countering Adversarial Perturbations by
Rewriting Text

Don't Retrain, Just Rewrite: Countering Adversarial Perturbations by Rewriting Text

Annual Meeting of the Association for Computational Linguistics (ACL), 2023

25 May 2023

Alakananda Vempala

ArXiv (abs)PDF HTML

Papers citing "Don't Retrain, Just Rewrite: Countering Adversarial Perturbations by Rewriting Text"

4 / 4 papers shown

Title
Backdoor Samples Detection Based on Perturbation Discrepancy Consistency in Pre-trained Language ModelsNeural Networks (NN), 2025 Zuquan Peng Jianming Fu Lixin Zou Li Zheng Yanzhen Ren Guojun Peng AAML 100 0 0 30 Aug 2025
SALMAN: Stability Analysis of Language Models Through the Maps Between Graph-based Manifolds Wuxinlin Cheng Yun Feng Jinwen Wu K. P. Subbalakshmi Tian Han Zhuo Feng AAML 96 0 0 23 Aug 2025
Exploring Gradient-Guided Masked Language Model to Detect Textual Adversarial Attacks Xiaomei Zhang Zhaoxi Zhang Yanjun Zhang Xufei Zheng L. Zhang Shengshan Hu Shirui Pan AAML 230 2 0 08 Apr 2025
Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression Zhichao Xu Ashim Gupta Tao Li Oliver Bentham Vivek Srikumar 400 20 0 06 Jul 2024