mlsanityData to 14 Oct 2026

PivotAttack: Rethinking the Search Trajectory in Hard-Label Text Attacks via Pivot Words

arXiv 2603.10842 ↗First posted 11 Mar 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Existing hard-label text attacks often rely on inefficient "outside-in" strategies that traverse vast search spaces. We propose PivotAttack, a query-efficient "inside-out" framework. It employs a Multi-Armed Bandit algorithm to identify Pivot Sets-combinatorial token groups acting as prediction anchors-and strategically perturbs them to induce label flips. This approach captures inter-word dependencies and minimizes query costs. Extensive experiments across traditional models and Large Language Models demonstrate that PivotAttack consistently outperforms state-of-the-art baselines in both Attack Success Rate and query efficiency.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 28 references that are in the map. First posted on arXiv 11 Mar 2026.

Builds on

14 of 28 references.

References · 14

  1. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  2. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,790
  3. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,682
  4. 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
  5. 2015A large annotated corpus for learning natural language inferencecited by 1,847
  6. 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 671
  7. 2017Supervised Learning of Universal Sentence Representations from Natural Language Inference Datacited by 432
  8. 2021Gradient-based Adversarial Attacks against Text Transformerscited by 234
  9. 2016Counter-fitting Word Vectors to Linguistic Constraintscited by 140
  10. 2020Generating Natural Language Attacks in a Hard Label Black Box Settingcited by 50
  11. 2022Query-Efficient and Scalable Black-Box Adversarial Attacks on Discrete Sequential Data via Bayesian Optimizationcited by 22
  12. 2020A Geometry-Inspired Attack for Generating Natural Language Adversarial Examplescited by 20
2 more
  1. 2022TextHacker: Learning based Hybrid Local Search Algorithm for Text Hard-label Adversarial Attackcited by 10
  2. 2023LimeAttack: Local Explainable Method for Textual Hard-Label Adversarial Attackcited by 9

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Strategic Sample Selection for Improved Clean-Label Backdoor Attacks in Text Classification
  2. 2023Large Language Models Are Better Adversaries: Exploring Generative Clean-Label Backdoor Attacks Against Text Classifiers
  3. 2025The Ultimate Cookbook for Invisible Poison: Crafting Subtle Clean-Label Text Backdoors with Style Attributes
  4. 2025Uncovering Competing Poisoning Attacks in Retrieval-Augmented Generation
  5. 2026Retrieved But Not Reliable: A Survey on Attacks, and Defenses in Retrieval-Augmented Generation
  6. 2024Backdoor Attacks on Dense Retrieval via Public and Unintentional Triggers
  7. 2026CamoDocs: A Poisoning Attack Against Retrieval-Augmented Language Models Using Camouflaged Documents
  8. 2026Retrieval Pivot Attacks in Hybrid RAG: Measuring and Mitigating Amplified Leakage from Vector Seeds to Graph Expansion