# Adversarial Attacks on Tables with Entity Swap

arXiv: https://arxiv.org/abs/2309.08650 · HTML: https://mlsanity.com/paper/2309.08650/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 16 references that are in the map.
- First posted on arXiv 15 Sep 2023.

## Builds on (most cited first, 9 of 9)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [BERT-ATTACK: Adversarial Attack Against BERT Using BERT](https://mlsanity.com/paper/2004.09984/) (2020)
- [Gradient-based Adversarial Attacks against Text Transformers](https://mlsanity.com/paper/2104.13733/) (2021)
- [Sherlock: A Deep Learning Approach to Semantic Data Type Detection](https://mlsanity.com/paper/1905.10688/) (2019)
- [Adversarial Attacks for Tabular Data: Application to Fraud Detection and Imbalanced Data](https://mlsanity.com/paper/2101.08030/) (2021)
- [Annotating Columns with Pre-trained Language Models](https://mlsanity.com/paper/2104.01785/) (2021)
- [Imperceptible Adversarial Attacks on Tabular Data](https://mlsanity.com/paper/1911.03274/) (2019)
- [Generating Table Vector Representations](https://mlsanity.com/paper/2110.15132/) (2021)

## Built on by (most cited first, 3 of 3)

- [Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks](https://mlsanity.com/paper/2310.10844/) (2023)
- [Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety](https://mlsanity.com/paper/2502.05206/) (2025)
- [Assessing biomedical knowledge robustness in large language models by query-efficient sampling attacks](https://mlsanity.com/paper/2402.10527/) (2024)

## Abstract (arXiv)

The capabilities of large language models (LLMs) have been successfully applied in the context of table representation learning. The recently proposed tabular language models have reported state-of-the-art results across various tasks for table interpretation. However, a closer look into the datasets commonly used for evaluation reveals an entity leakage from the train set into the test set. Motivated by this observation, we explore adversarial attacks that represent a more realistic inference setup. Adversarial attacks on text have been shown to greatly affect the performance of LLMs, but currently, there are no attacks targeting tabular language models. In this paper, we propose an evasive entity-swap attack for the column type annotation (CTA) task. Our CTA attack is the first black-box attack on tables, where we employ a similarity-based sampling strategy to generate adversarial examples. The experimental results show that the proposed attack generates up to a 70% drop in performance.