paper-with-me

홈 › Papers

Randomized Smoothing with Masked Inference for Adversarially Robust Text Classifications

2023-05-11 · Han Cheol Moon, Shafiq Joty, Ruochen Zhao, Megh Thakkar, Xu Chi

Large-scale pre-trained language models have shown outstanding performance in a variety of NLP tasks. However, they are also known to be significantly brittle against specifically crafted adversarial examples, leading to increasing interest in probing the adversarial robustness of NLP systems. We introduce RSMI, a novel two-stage framework that combines randomized smoothing (RS) with masked inference (MI) to improve the adversarial robustness of NLP systems. RS transforms a classifier into a smoothed classifier to obtain robust representations, whereas MI forces a model to exploit the surrounding context of a masked token in an input sequence. RSMI improves adversarial robustness by 2 to 3 times over existing state-of-the-art methods on benchmark datasets. We also perform in-depth qualitative analysis to validate the effectiveness of the different stages of RSMI and probe the impact of its components through extensive ablations. By empirically proving the stability of RSMI, we put it forward as a practical method to robustly train large-scale NLP models. Our code and datasets are available at https://github.com/Han8931/rsmi_nlp

📄 PDF Abstract BibTeX arXiv:2305.06522

Code (1)

han8931/rsmi_nlp 공식 구현 pytorch

Tasks

Adversarial Robustness

Methods 이 논문이 사용한 방법론

Randomized Smoothing 설명 없음

Similar Papers 제목 키워드 기반

Certified Adversarial Robustness via Randomized Smoothing

2019-02-08 · Jeremy M Cohen, Elan Rosenfeld, J. Zico Kolter

We show how to turn any classifier that classifies well under Gaussian noise into a new classifier that is certifiably robust to adversarial perturbations under the $\ell_2$ norm. This "randomized smoothing" technique ha…

Adversarial DefenseAdversarial RobustnessRobust classification

Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers

2019-06-09 · NeurIPS 2019 12 · Hadi Salman, Greg Yang, Jerry Li, Pengchuan Zhang 외

Recent works have shown the effectiveness of randomized smoothing as a scalable technique for building neural network-based classifiers that are provably robust to $\ell_2$-norm adversarial perturbations. In this paper, …

Adversarial AttackAdversarial DefenseDeep Learning

Towards Bridging the gap between Empirical and Certified Robustness against Adversarial Examples

2021-02-09 · Jay Nandy, Sudipan Saha, Wynne Hsu, Mong Li Lee 외

The current state-of-the-art defense methods against adversarial examples typically focus on improving either empirical or certified robustness. Among them, adversarially trained (AT) models produce empirical state-of-th…

Adversarial Robustness

Smoothed Inference for Adversarially-Trained Models

2019-11-17 · Yaniv Nemcovsky, Evgenii Zheltonozhskii, Chaim Baskin, Brian Chmiel 외

Deep neural networks are known to be vulnerable to adversarial attacks. Current methods of defense from such attacks are based on either implicit or explicit regularization, e.g., adversarial training. Randomized smoothi…

Adversarial Defense

Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networks

2023-01-05 · Yan Scholten, Jan Schuchardt, Simon Geisler, Aleksandar Bojchevski 외

Randomized smoothing is one of the most promising frameworks for certifying the adversarial robustness of machine learning models, including Graph Neural Networks (GNNs). Yet, existing randomized smoothing certificates f…

Adversarial Robustness