Experiments with adversarial attacks on text genres
Neural models based on pre-trained transformers, such as BERT or XLM-RoBERTa, demonstrate SOTA results in many NLP tasks, including non-topical classification, such as genre identification. However, often these approaches exhibit low reliability to minor alterations of the test texts. One of the problems concerns topical biases in the training corpus, for example, the prevalence of words on a specific topic in a specific genre can trick the genre classifier to recognise any text on this topic in this genre. In order to mitigate this problem, we investigate techniques for attacking genre classifiers to understand the limitations of the transformer models and to improve their performance. While simple text attacks, such as those based on word replacement using keywords extracted by tf-idf, are not capable of deceiving powerful models like XLM-RoBERTa, we show that embedding-based algorithms which can replace some of the most ``significant'' words with words similar to them, for example, TextFooler, have the ability to influence model predictions in a significant proportion of cases.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Experiments with adversarial attacks on text genres
Neural models based on pre-trained transformers, such as BERT or XLM-RoBERTa, demonstrate SOTA results in many NLP tasks, including non-topical classification, such as genre identification. However, often these approache…
A Brand New Dance Partner: Music-Conditioned Pluralistic Dancing Controlled by Multiple Dance Genres
When coming up with phrases of movement, choreographers all have their habits as they are used to their skilled dance genres. Therefore, they tend to return certain patterns of the dance genres that they are familiar…
Generative Adversarial NetworkMotion SynthesisWhat do we Really Know about State of the Art NER?
Named Entity Recognition (NER) is a well researched NLP task and is widely used in real world NLP scenarios. NER research typically focuses on the creation of new ways of training NER, with relatively less emphasis on re…
named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NERRebuild and Ensemble: Exploring Defense Against Text Adversaries
Adversarial attacks can mislead strong neural models; as such, in NLP tasks, substitution-based attacks are difficult to defend. Current defense methods usually assume that the substitution candidates are accessible, wh…
Adversarial DefenseMind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer
Adversarial attacks and backdoor attacks are two common security threats that hang over deep learning. Both of them harness task-irrelevant features of data in their implementation. Text style is a feature that is natura…
Adversarial AttackBackdoor AttackSentenceStyle Transfer+1