# Advancing NLP Security by Leveraging LLMs as Adversarial Engines

arXiv: https://arxiv.org/abs/2410.18215 · HTML: https://mlsanity.com/paper/2410.18215/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 21 references that are in the map.
- First posted on arXiv 23 Oct 2024.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [Large Language Models: A Survey](https://mlsanity.com/paper/2402.06196/) (2024)
- [AI Alignment: A Comprehensive Survey](https://mlsanity.com/paper/2310.19852/) (2023)
- [Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning](https://mlsanity.com/paper/2108.13888/) (2021)
- [Towards Improving Adversarial Training of NLP Models](https://mlsanity.com/paper/2109.00544/) (2021)
- [Adversarial attacks and defenses in explainable artificial intelligence: A survey](https://mlsanity.com/paper/2306.06123/) (2023)
- [MalBERT: Using Transformers for Cybersecurity and Malicious Software Detection](https://mlsanity.com/paper/2103.03806/) (2021)
- [Generating Valid and Natural Adversarial Examples with Large Language Models](https://mlsanity.com/paper/2311.11861/) (2023)
- [Fast Adversarial Training against Textual Adversarial Attacks](https://mlsanity.com/paper/2401.12461/) (2024)

## Abstract (arXiv)

This position paper proposes a novel approach to advancing NLP security by leveraging Large Language Models (LLMs) as engines for generating diverse adversarial attacks. Building upon recent work demonstrating LLMs' effectiveness in creating word-level adversarial examples, we argue for expanding this concept to encompass a broader range of attack types, including adversarial patches, universal perturbations, and targeted attacks. We posit that LLMs' sophisticated language understanding and generation capabilities can produce more effective, semantically coherent, and human-like adversarial examples across various domains and classifier architectures. This paradigm shift in adversarial NLP has far-reaching implications, potentially enhancing model robustness, uncovering new vulnerabilities, and driving innovation in defense mechanisms. By exploring this new frontier, we aim to contribute to the development of more secure, reliable, and trustworthy NLP systems for critical applications.