Unifying Adversarial Robustness and Training Across Text Scoring Models

• URL: http://arxiv.org/abs/2602.00857v1
• Date: Sat, 31 Jan 2026 18:41:04 GMT
• Title: Unifying Adversarial Robustness and Training Across Text Scoring Models
• Authors: Manveer Singh Tamber, Hosna Oyarhoseini, Jimmy Lin,
• Abstract summary: Research on adversarial robustness in language models is currently fragmented across applications and attacks.<n>We propose unifying the study of adversarial robustness in text scoring models spanning dense retrievers, rerankers, and reward models.
• Score: 43.70128463554434
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Research on adversarial robustness in language models is currently fragmented across applications and attacks, obscuring shared vulnerabilities. In this work, we propose unifying the study of adversarial robustness in text scoring models spanning dense retrievers, rerankers, and reward models. This motivates adapting both attacks and adversarial training methods across model roles. Unlike open-ended generation, text scoring failures are directly testable: an attack succeeds when an irrelevant or rejected text outscores a relevant or chosen one. Using this principled lens of text scoring, we demonstrate that current adversarial training formulations for language models are often short-sighted, failing to effectively generalize across attacks. To address this, we introduce multiple adversarial training methods for text scoring models and show that combining complementary training methods can yield strong robustness while also improving task effectiveness. We also highlight the practical value of our approach for RLHF, showing that our adversarially trained reward models mitigate reward hacking and support the training of better-aligned LLMs. We provide our code and models for further study.

Related papers

• Adversarial Training for Defense Against Label Poisoning Attacks [53.893792844055106]
  Label poisoning attacks pose significant risks to machine learning models.<n>We propose a novel adversarial training defense strategy based on support vector machines (SVMs) to counter these threats.<n>Our approach accommodates various model architectures and employs a projected gradient descent algorithm with kernel SVMs for adversarial training.
  arXiv  Detail & Related papers  (2025-02-24T13:03:19Z)
• Adversarial Robustification via Text-to-Image Diffusion Models [56.37291240867549]
  Adrial robustness has been conventionally believed as a challenging property to encode for neural networks. We develop a scalable and model-agnostic solution to achieve adversarial robustness without using any data.
  arXiv  Detail & Related papers  (2024-07-26T10:49:14Z)
• MirrorCheck: Efficient Adversarial Defense for Vision-Language Models [55.73581212134293]
  We propose a novel, yet elegantly simple approach for detecting adversarial samples in Vision-Language Models. Our method leverages Text-to-Image (T2I) models to generate images based on captions produced by target VLMs. Empirical evaluations conducted on different datasets validate the efficacy of our approach.
  arXiv  Detail & Related papers  (2024-06-13T15:55:04Z)
• Large Language Models Are Better Adversaries: Exploring Generative Clean-Label Backdoor Attacks Against Text Classifiers [25.94356063000699]
  Backdoor attacks manipulate model predictions by inserting innocuous triggers into training and test data. We focus on more realistic and more challenging clean-label attacks where the adversarial training examples are correctly labeled. Our attack, LLMBkd, leverages language models to automatically insert diverse style-based triggers into texts.
  arXiv  Detail & Related papers  (2023-10-28T06:11:07Z)
• SCAT: Robust Self-supervised Contrastive Learning via Adversarial Training for Text Classification [15.932462099791307]
  We propose a novel learning framework called SCAT (Self-supervised Contrastive Learning via Adversarial Training) SCAT modifies random augmentations of the data in a fully labelfree manner to generate adversarial examples. Our results show that SCAT can not only train robust language models from scratch, but it can also significantly improve the robustness of existing pre-trained language models.
  arXiv  Detail & Related papers  (2023-07-04T05:41:31Z)
• Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models [86.02610674750345]
  Adversarial GLUE (AdvGLUE) is a new multi-task benchmark to explore and evaluate the vulnerabilities of modern large-scale language models under various types of adversarial attacks. We apply 14 adversarial attack methods to GLUE tasks to construct AdvGLUE, which is further validated by humans for reliable annotations. All the language models and robust training methods we tested perform poorly on AdvGLUE, with scores lagging far behind the benign accuracy.
  arXiv  Detail & Related papers  (2021-11-04T12:59:55Z)
• Self-Supervised Contrastive Learning with Adversarial Perturbations for Robust Pretrained Language Models [18.726529370845256]
  This paper improves the robustness of the pretrained language model BERT against word substitution-based adversarial attacks. We also create an adversarial attack for word-level adversarial training on BERT.
  arXiv  Detail & Related papers  (2021-07-15T21:03:34Z)
• Learning to Attack: Towards Textual Adversarial Attacking in Real-world Situations [81.82518920087175]
  Adversarial attacking aims to fool deep neural networks with adversarial examples. We propose a reinforcement learning based attack model, which can learn from attack history and launch attacks more efficiently.
  arXiv  Detail & Related papers  (2020-09-19T09:12:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.