A One-Layer Decoder-Only Transformer is a Two-Layer RNN: With an Application to Certified Robustness

27 May 2024

Papers citing "A One-Layer Decoder-Only Transformer is a Two-Layer RNN: With an Application to Certified Robustness"

4 / 4 papers shown

Title
Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks Xinyu Zhang Hanbin Hong Yuan Hong Peng Huang Binghui Wang Zhongjie Ba Kui Ren SILM 86 24 0 31 Jul 2023
Robustness Verification for Transformers Zhouxing Shi Huan Zhang Kai-Wei Chang Minlie Huang Cho-Jui Hsieh AAML 71 107 0 16 Feb 2020
Certified Adversarial Robustness via Randomized Smoothing Jeremy M. Cohen Elan Rosenfeld J. Zico Kolter AAML 130 2,028 0 08 Feb 2019
Towards Deep Learning Models Resistant to Adversarial Attacks Aleksander Madry Aleksandar Makelov Ludwig Schmidt Dimitris Tsipras Adrian Vladu SILM OOD 269 12,029 0 19 Jun 2017