A Differentiable Language Model Adversarial Attack on Text Classifiers

• URL: http://arxiv.org/abs/2107.11275v1
• Date: Fri, 23 Jul 2021 14:43:13 GMT
• Title: A Differentiable Language Model Adversarial Attack on Text Classifiers
• Authors: Ivan Fursov, Alexey Zaytsev, Pavel Burnyshev, Ekaterina Dmitrieva, Nikita Klyuchnikov, Andrey Kravchenko, Ekaterina Artemova, Evgeny Burnaev
• Abstract summary: We propose a new black-box sentence-level attack for natural language processing. Our method fine-tunes a pre-trained language model to generate adversarial examples. We show that the proposed attack outperforms competitors on a diverse set of NLP problems for both computed metrics and human evaluation.
• Score: 10.658675415759697
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Robustness of huge Transformer-based models for natural language processing is an important issue due to their capabilities and wide adoption. One way to understand and improve robustness of these models is an exploration of an adversarial attack scenario: check if a small perturbation of an input can fool a model. Due to the discrete nature of textual data, gradient-based adversarial methods, widely used in computer vision, are not applicable per~se. The standard strategy to overcome this issue is to develop token-level transformations, which do not take the whole sentence into account. In this paper, we propose a new black-box sentence-level attack. Our method fine-tunes a pre-trained language model to generate adversarial examples. A proposed differentiable loss function depends on a substitute classifier score and an approximate edit distance computed via a deep learning model. We show that the proposed attack outperforms competitors on a diverse set of NLP problems for both computed metrics and human evaluation. Moreover, due to the usage of the fine-tuned language model, the generated adversarial examples are hard to detect, thus current models are not robust. Hence, it is difficult to defend from the proposed attack, which is not the case for other attacks.

Related papers

• Robustifying Language Models with Test-Time Adaptation [17.96043752001886]
  Large-scale language models achieved state-of-the-art performance over a number of language tasks. They fail on adversarial language examples, which are sentences optimized to fool the language models but with similar semantic meanings for humans. We show that we can reverse many language adversarial attacks by adapting the input sentence with predictions from masked words.
  arXiv  Detail & Related papers  (2023-10-29T22:37:54Z)
• LimeAttack: Local Explainable Method for Textual Hard-Label Adversarial Attack [3.410883081705873]
  We propose a novel hard-label attack algorithm named LimeAttack. We show that LimeAttack achieves the better attacking performance compared with existing hard-label attack. adversarial examples crafted by LimeAttack are highly transferable and effectively improve model robustness in adversarial training.
  arXiv  Detail & Related papers  (2023-08-01T06:30:37Z)
• Are aligned neural networks adversarially aligned? [93.91072860401856]
  adversarial users can construct inputs which circumvent attempts at alignment. We show that existing NLP-based optimization attacks are insufficiently powerful to reliably attack aligned text models. We conjecture that improved NLP attacks may demonstrate this same level of adversarial control over text-only models.
  arXiv  Detail & Related papers  (2023-06-26T17:18:44Z)
• On Evaluating the Adversarial Robustness of Semantic Segmentation Models [0.0]
  A number of adversarial training approaches have been proposed as a defense against adversarial perturbation. We show for the first time that a number of models in previous work that are claimed to be robust are in fact not robust at all. We then evaluate simple adversarial training algorithms that produce reasonably robust models even under our set of strong attacks.
  arXiv  Detail & Related papers  (2023-06-25T11:45:08Z)
• 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)
• Towards Variable-Length Textual Adversarial Attacks [68.27995111870712]
  It is non-trivial to conduct textual adversarial attacks on natural language processing tasks due to the discreteness of data. In this paper, we propose variable-length textual adversarial attacks(VL-Attack) Our method can achieve $33.18$ BLEU score on IWSLT14 German-English translation, achieving an improvement of $1.47$ over the baseline model.
  arXiv  Detail & Related papers  (2021-04-16T14:37:27Z)
• 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)
• Defense against Adversarial Attacks in NLP via Dirichlet Neighborhood Ensemble [163.3333439344695]
  Dirichlet Neighborhood Ensemble (DNE) is a randomized smoothing method for training a robust model to defense substitution-based attacks. DNE forms virtual sentences by sampling embedding vectors for each word in an input sentence from a convex hull spanned by the word and its synonyms, and it augments them with the training data. We demonstrate through extensive experimentation that our method consistently outperforms recently proposed defense methods by a significant margin across different network architectures and multiple data sets.
  arXiv  Detail & Related papers  (2020-06-20T18:01:16Z)
• Differentiable Language Model Adversarial Attacks on Categorical Sequence Classifiers [0.0]
  An adversarial attack paradigm explores various scenarios for the vulnerability of deep learning models. We use a fine-tuning of a language model for adversarial attacks as a generator of adversarial examples. Our model works for diverse datasets on bank transactions, electronic health records, and NLP datasets.
  arXiv  Detail & Related papers  (2020-06-19T11:25:36Z)
• Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations [65.05561023880351]
  Adversarial examples are malicious inputs crafted to induce misclassification. This paper studies a complementary failure mode, invariance-based adversarial examples. We show that defenses against sensitivity-based attacks actively harm a model's accuracy on invariance-based attacks.
  arXiv  Detail & Related papers  (2020-02-11T18:50:23Z)

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.