# Adversarial Attacks and Defense for Conversation Entailment Task

arXiv: https://arxiv.org/abs/2405.00289 · HTML: https://mlsanity.com/paper/2405.00289/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 22 references that are in the map.
- First posted on arXiv 1 May 2024.

## Builds on (most cited first, 14 of 14)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [Generating Natural Language Adversarial Examples](https://mlsanity.com/paper/1804.07998/) (2018)
- [TextBugger: Generating Adversarial Text Against Real-world Applications](https://mlsanity.com/paper/1812.05271/) (2018)
- [Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers](https://mlsanity.com/paper/1801.04354/) (2018)
- [Combating Adversarial Misspellings with Robust Word Recognition](https://mlsanity.com/paper/1905.11268/) (2019)
- [Adversarial Training for Large Neural Language Models](https://mlsanity.com/paper/2004.08994/) (2020)
- [GO FIGURE: A Meta Evaluation of Factuality in Summarization](https://mlsanity.com/paper/2010.12834/) (2020)
- [Adversarial Machine Learning in Image Classification: A Survey Towards the Defender's Perspective](https://mlsanity.com/paper/2009.03728/) (2020)
- [HotFlip: White-Box Adversarial Examples for Text Classification](https://mlsanity.com/paper/1712.06751/) (2017)
- [Word Embedding Perturbation for Sentence Classification](https://mlsanity.com/paper/1804.08166/) (2018)
- [An Orthogonal Classifier for Improving the Adversarial Robustness of Neural Networks](https://mlsanity.com/paper/2105.09109/) (2021)
- [Beyond the Tip of the Iceberg: Assessing Coherence of Text Classifiers](https://mlsanity.com/paper/2109.04922/) (2021)

## Abstract (arXiv)

As the deployment of NLP systems in critical applications grows, ensuring the robustness of large language models (LLMs) against adversarial attacks becomes increasingly important. Large language models excel in various NLP tasks but remain vulnerable to low-cost adversarial attacks. Focusing on the domain of conversation entailment, where multi-turn dialogues serve as premises to verify hypotheses, we fine-tune a transformer model to accurately discern the truthfulness of these hypotheses. Adversaries manipulate hypotheses through synonym swapping, aiming to deceive the model into making incorrect predictions. To counteract these attacks, we implemented innovative fine-tuning techniques and introduced an embedding perturbation loss method to significantly bolster the model's robustness. Our findings not only emphasize the importance of defending against adversarial attacks in NLP but also highlight the real-world implications, suggesting that enhancing model robustness is critical for reliable NLP applications.