AdaptDel: Adaptable Deletion Rate Randomized Smoothing for Certified Robustness
Not on the map. Why?
Abstract (arXiv)
We consider the problem of certified robustness for sequence classification against edit distance perturbations. Naturally occurring inputs of varying lengths (e.g., sentences in natural language processing tasks) present a challenge to current methods that employ fixed-rate deletion mechanisms and lead to suboptimal performance. To this end, we introduce AdaptDel methods with adaptable deletion rates that dynamically adjust based on input properties. We extend the theoretical framework of randomized smoothing to variable-rate deletion, ensuring sound certification with respect to edit distance. We achieve strong empirical results in natural language tasks, observing up to 30 orders of magnitude improvement to median cardinality of the certified region, over state-of-the-art certifications.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 30 of its 47 references that are in the map. First posted on arXiv 12 Nov 2025.
Builds on
30 of 47 references.
References · 30
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
- 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
- 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 663
- 2020BERT-ATTACK: Adversarial Attack Against BERT Using BERTcited by 488
- 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
- 2018Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifierscited by 341
- 2020BAE: BERT-based Adversarial Examples for Text Classificationcited by 316
- 2017Synthetic and Natural Noise Both Break Neural Machine Translationcited by 304
- 2019FreeLB: Enhanced Adversarial Training for Natural Language Understandingcited by 261
- 2019Certified Robustness to Adversarial Word Substitutionscited by 164
- 2020Contextualized Perturbation for Textual Adversarial Attackcited by 136
18 more
- 2022Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLPcited by 99
- 2019Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagationcited by 87
- 2020SAFER: A Structure-free Approach for Certified Robustness to Adversarial Word Substitutionscited by 72
- 2019Tight Certificates of Adversarial Robustness for Randomly Smoothed Classifierscited by 65
- 2021Certified Robustness to Text Adversarial Attacks by Randomized [MASK]cited by 57
- 2020Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and Morecited by 56
- 2019Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized Smoothingcited by 54
- 2021PointGuard: Provably Robust 3D Point Cloud Classificationcited by 49
- 2020Data-Dependent Randomized Smoothingcited by 37
- 2023Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attackscited by 32
- 2021Intriguing Properties of Input-dependent Randomized Smoothingcited by 24
- 2021Achieving Model Robustness through Discrete Adversarial Trainingcited by 23
- 2021ANCER: Anisotropic Certification via Sample-wise Volume Maximizationcited by 23
- 2023RS-Del: Edit Distance Robustness Certificates for Sequence Classifiers via Randomized Deletioncited by 17
- 2024Advancing the Robustness of Large Language Models through Self-Denoised Smoothingcited by 15
- 2024Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defencescited by 9
- 2023Provable Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and Morecited by 3
- 2024CERT-ED: Certifiably Robust Text Classification for Edit Distancecited by 2
Built on by
Not cited yet.