Adversarially Pretrained Transformers may be Universally Robust In-Context Learners

20 May 2025

Soichiro Kumano

Hiroshi Kera

Toshihiko Yamasaki

Author Contacts:

kumano@cvm.t.u-tokyo.ac.jp kera@chiba-u.jp yamasaki@cvm.t.u-tokyo.ac.jp

AAML

ArXiv (abs)PDF HTML

Papers citing "Adversarially Pretrained Transformers may be Universally Robust In-Context Learners"

36 / 86 papers shown

Title
Reliably fast adversarial training via latent adversarial perturbation Geon Yeong Park Sang Wan Lee AAML 56 28 0 04 Apr 2021
On the Robustness of Vision Transformers to Adversarial Examples Kaleel Mahmood Rigel Mahmood Marten van Dijk ViT 118 224 0 31 Mar 2021
On the Adversarial Robustness of Vision Transformers Rulin Shao Zhouxing Shi Jinfeng Yi Pin-Yu Chen Cho-Jui Hsieh ViT 72 142 0 29 Mar 2021
Understanding Robustness of Transformers for Image Classification Srinadh Bhojanapalli Ayan Chakrabarti Daniel Glasner Daliang Li Thomas Unterthiner Andreas Veit ViT 90 385 0 26 Mar 2021
On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning Ren Wang Kaidi Xu Sijia Liu Pin-Yu Chen Tsui-Wei Weng Chuang Gan Meng Wang AAML 80 47 0 20 Feb 2021
Fundamental Tradeoffs in Distributionally Adversarial Training M. Mehrabi Adel Javanmard Ryan A. Rossi Anup B. Rao Tung Mai AAML 51 18 0 15 Jan 2021
A Simple Fine-tuning Is All You Need: Towards Robust Deep Learning Via Adversarial Fine-tuning Ahmadreza Jeddi M. Shafiee A. Wong AAML 67 39 0 25 Dec 2020
Extracting Training Data from Large Language Models Nicholas Carlini Florian Tramèr Eric Wallace Matthew Jagielski Ariel Herbert-Voss ... Tom B. Brown Basel Alomair Ulfar Erlingsson Alina Oprea Colin Raffel MLAU SILM 489 1,923 0 14 Dec 2020
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai ... Matthias Minderer G. Heigold Sylvain Gelly Jakob Uszkoreit N. Houlsby ViT 657 41,103 0 22 Oct 2020
Understanding Catastrophic Overfitting in Single-step Adversarial Training Hoki Kim Woojin Lee Jaewook Lee AAML 102 112 0 05 Oct 2020
Understanding and Improving Fast Adversarial Training Maksym Andriushchenko Nicolas Flammarion AAML 79 290 0 06 Jul 2020
Provable tradeoffs in adversarially robust classification Yan Sun Hamed Hassani David Hong Alexander Robey 60 56 0 09 Jun 2020
Language Models are Few-Shot Learners Tom B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan ... Christopher Berner Sam McCandlish Alec Radford Ilya Sutskever Dario Amodei BDL 798 42,055 0 28 May 2020
BAE: BERT-based Adversarial Examples for Text Classification Siddhant Garg Goutham Ramakrishnan AAML SILM 198 556 0 04 Apr 2020
Adversarial Robustness on In- and Out-Distribution Improves Explainability Maximilian Augustin Alexander Meinke Matthias Hein OOD 157 102 0 20 Mar 2020
Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks Francesco Croce Matthias Hein AAML 216 1,846 0 03 Mar 2020
Understanding and Mitigating the Tradeoff Between Robustness and Accuracy Aditi Raghunathan Sang Michael Xie Fanny Yang John C. Duchi Percy Liang AAML 87 228 0 25 Feb 2020
On Adaptive Attacks to Adversarial Example Defenses Florian Tramèr Nicholas Carlini Wieland Brendel Aleksander Madry AAML 277 834 0 19 Feb 2020
Fast is better than free: Revisiting adversarial training Eric Wong Leslie Rice J. Zico Kolter AAML OOD 138 1,179 0 12 Jan 2020
Are Perceptually-Aligned Gradients a General Property of Robust Classifiers? Simran Kaur Jeremy M. Cohen Zachary Chase Lipton OOD AAML 51 66 0 18 Oct 2019
Universal Adversarial Triggers for Attacking and Analyzing NLP Eric Wallace Shi Feng Nikhil Kandpal Matt Gardner Sameer Singh AAML SILM 114 866 0 20 Aug 2019
Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment Di Jin Zhijing Jin Qiufeng Wang Peter Szolovits SILM AAML 179 1,078 0 27 Jul 2019
Adversarial Training Can Hurt Generalization Aditi Raghunathan Sang Michael Xie Fanny Yang John C. Duchi Percy Liang 82 243 0 14 Jun 2019
Interpreting Adversarially Trained Convolutional Neural Networks Tianyuan Zhang Zhanxing Zhu AAML GAN FAtt 100 161 0 23 May 2019
On the Connection Between Adversarial Robustness and Saliency Map Interpretability Christian Etmann Sebastian Lunz Peter Maass Carola-Bibiane Schönlieb AAML FAtt 58 162 0 10 May 2019
Adversarial Examples Are Not Bugs, They Are Features Andrew Ilyas Shibani Santurkar Dimitris Tsipras Logan Engstrom Brandon Tran Aleksander Madry SILM 91 1,838 0 06 May 2019
You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle Dinghuai Zhang Tianyuan Zhang Yiping Lu Zhanxing Zhu Bin Dong AAML 109 361 0 02 May 2019
Theoretically Principled Trade-off between Robustness and Accuracy Hongyang R. Zhang Yaodong Yu Jiantao Jiao Eric Xing L. Ghaoui Michael I. Jordan 137 2,551 0 24 Jan 2019
Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Models D. Su Huan Zhang Hongge Chen Jinfeng Yi Pin-Yu Chen Yupeng Gao VLM 128 391 0 05 Aug 2018
Adversarial Meta-Learning Chengxiang Yin Jian Tang Zhiyuan Xu Yanzhi Wang 64 42 0 08 Jun 2018
Robustness May Be at Odds with Accuracy Dimitris Tsipras Shibani Santurkar Logan Engstrom Alexander Turner Aleksander Madry AAML 104 1,781 0 30 May 2018
Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples Anish Athalye Nicholas Carlini D. Wagner AAML 226 3,186 0 01 Feb 2018
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms Han Xiao Kashif Rasul Roland Vollgraf 283 8,904 0 25 Aug 2017
Towards Deep Learning Models Resistant to Adversarial Attacks Aleksander Madry Aleksandar Makelov Ludwig Schmidt Dimitris Tsipras Adrian Vladu SILM OOD 307 12,069 0 19 Jun 2017
Explaining and Harnessing Adversarial Examples Ian Goodfellow Jonathon Shlens Christian Szegedy AAML GAN 277 19,066 0 20 Dec 2014
Intriguing properties of neural networks Christian Szegedy Wojciech Zaremba Ilya Sutskever Joan Bruna D. Erhan Ian Goodfellow Rob Fergus AAML 275 14,927 1 21 Dec 2013