No article text was recorded for this version.
perturbation scope limitation
Version 1 of 137 papers42 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Phrase-level Textual Adversarial Attack with Label Preservation
- Blog: AdvExpander: Generating Natural Language Adversarial Examples by Expanding Text
- Blog: Revisiting Character-level Adversarial Attacks for Language Models
- Blog: Evaluating the Validity of Word-level Adversarial Attacks with Large Language Models
- Blog: Achieving Model Robustness through Discrete Adversarial Training
- Blog: Defending Pre-trained Language Models from Adversarial Word Substitution Without Performance Sacrifice
- Blog: CheckHARD: Checking Hard Labels for Adversarial Text Detection, Prediction Correction, and Perturbed Word Suggestion
- Blog: Word Level Robustness Enhancement: Fight Perturbation with Perturbation
- Blog: Towards Robustness Against Natural Language Word Substitutions
- Blog: Better Robustness by More Coverage: Adversarial and Mixup Data Augmentation for Robust Finetuning
- Blog: ValCAT: Variable-Length Contextualized Adversarial Transformations Using Encoder-Decoder Language Model
- Blog: Robustness-Aware Word Embedding Improves Certified Robustness to Adversarial Word Substitutions
- Blog: Detecting textual adversarial examples through randomized substitution and vote
- Blog: In and Out-of-Domain Text Adversarial Robustness via Label Smoothing
- Blog: TextVerifier: Robustness Verification for Textual Classifiers with Certifiable Guarantees
- Blog: TextFirewall: Omni-Defending Against Adversarial Texts in Sentiment Classification
- Blog: SeqAttack: On Adversarial Attacks for Named Entity Recognition
- Blog: Detecting Word-Level Adversarial Text Attacks via SHapley Additive exPlanations
- Blog: A Sweet Rabbit Hole by DARCY: Using Honeypots to Detect Universal Trigger's Adversarial Attacks
- Blog: Adversarial Training for Improving Model Robustness? Look at Both Prediction and Interpretation
- Blog: Single Word Change Is All You Need: Using LLMs to Create Synthetic Training Examples for Text Classifiers
- Blog: Robust textual embedding against word-level adversarial attacks
- Blog: Frequency-Guided Word Substitutions for Detecting Textual Adversarial Examples
- Blog: Generating Natural Language Adversarial Examples
- Blog: White-to-Black: Efficient Distillation of Black-Box Adversarial Attacks
- Blog: Defense against Synonym Substitution-based Adversarial Attacks via Dirichlet Neighborhood Ensemble
- Blog: Robust Few-Shot Named Entity Recognition with Boundary Discrimination and Correlation Purification
- Blog: RMLM: A Flexible Defense Framework for Proactively Mitigating Word-level Adversarial Attacks
- Blog: InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective
- Blog: Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords Substitution
- Blog: Weight Perturbation as Defense against Adversarial Word Substitutions
- Blog: Similarizing the Influence of Words with Contrastive Learning to Defend Word-level Adversarial Text Attack
- Blog: CharBERT: Character-aware Pre-trained Language Model
- Blog: RoChBert: Towards Robust BERT Fine-tuning for Chinese
- Blog: TextShield: Beyond Successfully Detecting Adversarial Sentences in text classification
- Blog: The Best Defense is Attack: Repairing Semantics in Textual Adversarial Examples
- Blog: Certified Robustness to Word Substitution Attack with Differential Privacy
History & citation
Current · Permanent link
- This direction split from Multi-Granular Robustness for Natural Language Processing (78% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_perturbation_scope_limitation_2c98572b,
title = {perturbation scope limitation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/perturbation-scope-limitation/rdr_2c98572bb1424971941e666978f78211},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_perturbation_scope_limitation_2c98572b_v1,
title = {perturbation scope limitation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/perturbation-scope-limitation/rdr_2c98572bb1424971941e666978f78211/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}