TSCheater: Generating High-Quality Tibetan Adversarial Texts via Visual Similarity

• URL: http://arxiv.org/abs/2412.02371v3
• Date: Thu, 26 Dec 2024 07:34:28 GMT
• Title: TSCheater: Generating High-Quality Tibetan Adversarial Texts via Visual Similarity
• Authors: Xi Cao, Quzong Gesang, Yuan Sun, Nuo Qun, Tashi Nyima,
• Abstract summary: We propose a novel Tibetan adversarial text generation method called TSCheater. It considers the characteristic of Tibetan encoding and the feature that visually similar syllables have similar semantics. Experimentally, TSCheater outperforms existing methods in attack effectiveness, perturbation, semantic similarity, visual similarity, and human acceptance.
• Score: 3.1854179230109363
• License:
• Abstract: Language models based on deep neural networks are vulnerable to textual adversarial attacks. While rich-resource languages like English are receiving focused attention, Tibetan, a cross-border language, is gradually being studied due to its abundant ancient literature and critical language strategy. Currently, there are several Tibetan adversarial text generation methods, but they do not fully consider the textual features of Tibetan script and overestimate the quality of generated adversarial texts. To address this issue, we propose a novel Tibetan adversarial text generation method called TSCheater, which considers the characteristic of Tibetan encoding and the feature that visually similar syllables have similar semantics. This method can also be transferred to other abugidas, such as Devanagari script. We utilize a self-constructed Tibetan syllable visual similarity database called TSVSDB to generate substitution candidates and adopt a greedy algorithm-based scoring mechanism to determine substitution order. After that, we conduct the method on eight victim language models. Experimentally, TSCheater outperforms existing methods in attack effectiveness, perturbation magnitude, semantic similarity, visual similarity, and human acceptance. Finally, we construct the first Tibetan adversarial robustness evaluation benchmark called AdvTS, which is generated by existing methods and proofread by humans.

Related papers

• Human-in-the-Loop Generation of Adversarial Texts: A Case Study on Tibetan Script [7.5950217558686255]
  Adversarial texts play crucial roles in multiple subfields of NLP. We introduce HITL-GAT, a system based on a general approach to human-in-the-loop generation of adversarial texts.
  arXiv  Detail & Related papers  (2024-12-17T02:29:54Z)
• Multi-Granularity Tibetan Textual Adversarial Attack Method Based on Masked Language Model [0.0]
  We propose a multi-granularity Tibetan textual adversarial attack method based on masked language models called TSTricker. Results show that TSTricker reduces the accuracy of the classification models by more than 28.70% and makes the classification models change the predictions of more than 90.60% of the samples.
  arXiv  Detail & Related papers  (2024-12-03T10:03:52Z)
• Pay Attention to the Robustness of Chinese Minority Language Models! Syllable-level Textual Adversarial Attack on Tibetan Script [0.0]
  Textual adversarial attacks are a new challenge for the information processing of Chinese minority languages. We propose a Tibetan syllable-level black-box textual adversarial attack called TSAttacker. Experiment results show that TSAttacker is effective and generates high-quality adversarial samples.
  arXiv  Detail & Related papers  (2024-12-03T09:38:22Z)
• Detecting Machine-Generated Long-Form Content with Latent-Space Variables [54.07946647012579]
  Existing zero-shot detectors primarily focus on token-level distributions, which are vulnerable to real-world domain shifts. We propose a more robust method that incorporates abstract elements, such as event transitions, as key deciding factors to detect machine versus human texts.
  arXiv  Detail & Related papers  (2024-10-04T18:42:09Z)
• Pixel Sentence Representation Learning [67.4775296225521]
  In this work, we conceptualize the learning of sentence-level textual semantics as a visual representation learning process. We employ visually-grounded text perturbation methods like typos and word order shuffling, resonating with human cognitive patterns, and enabling perturbation to be perceived as continuous. Our approach is further bolstered by large-scale unsupervised topical alignment training and natural language inference supervision.
  arXiv  Detail & Related papers  (2024-02-13T02:46:45Z)
• Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning [61.34060587461462]
  We propose a two-stage framework for Chinese Text Recognition (CTR) We pre-train a CLIP-like model through aligning printed character images and Ideographic Description Sequences (IDS) This pre-training stage simulates humans recognizing Chinese characters and obtains the canonical representation of each character. The learned representations are employed to supervise the CTR model, such that traditional single-character recognition can be improved to text-line recognition.
  arXiv  Detail & Related papers  (2023-09-03T05:33:16Z)
• A New Generation of Perspective API: Efficient Multilingual Character-level Transformers [66.9176610388952]
  We present the fundamentals behind the next version of the Perspective API from Google Jigsaw. At the heart of the approach is a single multilingual token-free Charformer model. We demonstrate that by forgoing static vocabularies, we gain flexibility across a variety of settings.
  arXiv  Detail & Related papers  (2022-02-22T20:55:31Z)
• A Aelf-supervised Tibetan-chinese Vocabulary Alignment Method Based On Adversarial Learning [3.553493344868414]
  This paper uses two monolingual corpora and a small number of seed dictionaries to learn the semi-supervised method with seed dictionaries and self-supervised adversarial training method. The experimental results of Tibetan syllables Chinese characters are not good, which reflects the weak semantic correlation between Tibetan syllables and Chinese characters.
  arXiv  Detail & Related papers  (2021-10-04T08:56:33Z)
• Coarse and Fine-Grained Hostility Detection in Hindi Posts using Fine Tuned Multilingual Embeddings [4.3012765978447565]
  The hostility detection task has been well explored for resource-rich languages like English, but is unexplored for resource-constrained languages like Hindidue to the unavailability of large suitable data. We propose an effective neural network-based technique for hostility detection in Hindi posts.
  arXiv  Detail & Related papers  (2021-01-13T11:00:31Z)
• Generating Adversarial Examples in Chinese Texts Using Sentence-Pieces [60.58900627906269]
  We propose a pre-train language model as the substitutes generator using sentence-pieces to craft adversarial examples in Chinese. The substitutions in the generated adversarial examples are not characters or words but textit'pieces', which are more natural to Chinese readers.
  arXiv  Detail & Related papers  (2020-12-29T14:28:07Z)
• Near-imperceptible Neural Linguistic Steganography via Self-Adjusting Arithmetic Coding [88.31226340759892]
  We present a new linguistic steganography method which encodes secret messages using self-adjusting arithmetic coding based on a neural language model. Human evaluations show that 51% of generated cover texts can indeed fool eavesdroppers.
  arXiv  Detail & Related papers  (2020-10-01T20:40:23Z)

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.