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

arXiv: https://arxiv.org/abs/2603.10842 · HTML: https://mlsanity.com/paper/2603.10842/

## 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 (most cited first, 14 of 14)

- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [Supervised Learning of Universal Sentence Representations from Natural Language Inference Data](https://mlsanity.com/paper/1705.02364/) (2017)
- [Gradient-based Adversarial Attacks against Text Transformers](https://mlsanity.com/paper/2104.13733/) (2021)
- [Counter-fitting Word Vectors to Linguistic Constraints](https://mlsanity.com/paper/1603.00892/) (2016)
- [Generating Natural Language Attacks in a Hard Label Black Box Setting](https://mlsanity.com/paper/2012.14956/) (2020)
- [Query-Efficient and Scalable Black-Box Adversarial Attacks on Discrete Sequential Data via Bayesian Optimization](https://mlsanity.com/paper/2206.08575/) (2022)
- [A Geometry-Inspired Attack for Generating Natural Language Adversarial Examples](https://mlsanity.com/paper/2010.01345/) (2020)
- [TextHacker: Learning based Hybrid Local Search Algorithm for Text Hard-label Adversarial Attack](https://mlsanity.com/paper/2201.08193/) (2022)
- [LimeAttack: Local Explainable Method for Textual Hard-Label Adversarial Attack](https://mlsanity.com/paper/2308.00319/) (2023)

## 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.