ValCAT: Variable-Length Contextualized Adversarial Transformations Using Encoder-Decoder Language Model
Adversarial texts help explore vulnerabilities in language models, improve model robustness, and explain their working mechanisms. However, existing word-level attack methods trap in a one-to-one attack pattern, i.e., only a single word can be modified in one transformation round, and they ignore the interactions between several consecutive words. In this paper, we propose ValCAT, a black-box attack framework that misleads the language model by applying variable-length contextualized transformations to the original text. Compared to word-level methods, ValCAT expands the basic units of perturbation from single words to spans composed of multiple consecutive words, enhancing the perturbation capability. Experiments show that our method outperforms state-of-the-art methods in terms of attack success rate, perplexity, and semantic similarity on several classification tasks and inference tasks. The comprehensive human evaluation demonstrates that ValCAT has a significant advantage in ensuring the fluency of the adversarial examples and achieves better semantic consistency. We release the code at https://github.com/linerxliner/ValCAT.
Code (1)
Tasks
DecoderLanguage ModelingLanguage ModellingSemantic SimilaritySemantic Textual SimilaritySimilar Papers 제목 키워드 기반
ValCAT: Generating Variable-Length Contextualized Adversarial Transformations using Encoder-Decoder
Adversarial samples are helpful to explore vulnerabilities in neural network models, improve model robustness, and explain their working mechanism. However, the adversarial texts generated by existing word substitution-b…
DecoderLanguage ModelingLanguage ModellingContextualized Perturbation for Textual Adversarial Attack
Adversarial examples expose the vulnerabilities of natural language processing (NLP) models, and can be used to evaluate and improve their robustness. Existing techniques of generating such examples are typically driven …
Adversarial AttackLanguage ModelingLanguage ModellingCertified Robustness to Adversarial Word Substitutions
State-of-the-art NLP models can often be fooled by adversaries that apply seemingly innocuous label-preserving transformations (e.g., paraphrasing) to input text. The number of possible transformations scales exponential…
Data AugmentationNatural Language InferenceSentiment AnalysisMulti-objective Evolutionary Search of Variable-length Composite Semantic Perturbations
Deep neural networks have proven to be vulnerable to adversarial attacks in the form of adding specific perturbations on images to make wrong outputs. Designing stronger adversarial attack methods can help more reliably …
Adversarial AttackAutoMLVQCPC-GAN: Variable-Length Adversarial Audio Synthesis Using Vector-Quantized Contrastive Predictive Coding
Influenced by the field of Computer Vision, Generative Adversarial Networks (GANs) are often adopted for the audio domain using fixed-size two-dimensional spectrogram representations as the "image data". However, in the …
Audio Synthesis