# DINA: A Dual Defense Framework Against Internal Noise and External Attacks in Natural Language Processing

arXiv: https://arxiv.org/abs/2508.05671 · HTML: https://mlsanity.com/paper/2508.05671/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 24 references that are in the map.
- First posted on arXiv 4 Aug 2025.

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

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://mlsanity.com/paper/2002.07394/) (2020)
- [BERT-ATTACK: Adversarial Attack Against BERT Using BERT](https://mlsanity.com/paper/2004.09984/) (2020)
- [Adversarial Training Methods for Semi-Supervised Text Classification](https://mlsanity.com/paper/1605.07725/) (2016)
- [Learning with Feature-Dependent Label Noise: A Progressive Approach](https://mlsanity.com/paper/2103.07756/) (2021)
- [Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise](https://mlsanity.com/paper/2012.05458/) (2020)
- [Towards Improving Adversarial Training of NLP Models](https://mlsanity.com/paper/2109.00544/) (2021)
- [Interpretable Adversarial Perturbation in Input Embedding Space for Text](https://mlsanity.com/paper/1805.02917/) (2018)
- [Natural Language Adversarial Defense through Synonym Encoding](https://mlsanity.com/paper/1909.06723/) (2019)
- [Unsupervised Domain Adaptation for Neural Machine Translation with Domain-Aware Feature Embeddings](https://mlsanity.com/paper/1908.10430/) (2019)
- [Noisy Label Processing for Classification: A Survey](https://mlsanity.com/paper/2404.04159/) (2024)
- [Learning to Detect Noisy Labels Using Model-Based Features](https://mlsanity.com/paper/2212.13767/) (2022)
- [Adversarial Training for Defense Against Label Poisoning Attacks](https://mlsanity.com/paper/2502.17121/) (2025)
- [Rethinking Noisy Label Models: Labeler-Dependent Noise with Adversarial Awareness](https://mlsanity.com/paper/2105.14083/) (2021)

## Abstract (arXiv)

As large language models (LLMs) and generative AI become increasingly integrated into customer service and moderation applications, adversarial threats emerge from both external manipulations and internal label corruption. In this work, we identify and systematically address these dual adversarial threats by introducing DINA (Dual Defense Against Internal Noise and Adversarial Attacks), a novel unified framework tailored specifically for NLP. Our approach adapts advanced noisy-label learning methods from computer vision and integrates them with adversarial training to simultaneously mitigate internal label sabotage and external adversarial perturbations. Extensive experiments conducted on a real-world dataset from an online gaming service demonstrate that DINA significantly improves model robustness and accuracy compared to baseline models. Our findings not only highlight the critical necessity of dual-threat defenses but also offer practical strategies for safeguarding NLP systems in realistic adversarial scenarios, underscoring broader implications for fair and responsible AI deployment.