paper-with-me

홈 › Papers

Experiments with adversarial attacks on text genres

2022-01-16 · ACL ARR January 2022 1 · Anonymous

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Adam 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

Experiments with adversarial attacks on text genres

2021-07-05 · Mikhail Lepekhin, Serge Sharoff

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

2022-01-01 · CVPR 2022 1 · Jinwoo Kim, Heeseok Oh, Seongjean Kim, Hoseok Tong 외

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 Synthesis

What do we Really Know about State of the Art NER?

2022-04-29 · LREC 2022 6 · Sowmya Vajjala, Ramya Balasubramaniam

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)NER

Rebuild and Ensemble: Exploring Defense Against Text Adversaries

2021-11-16 · ACL ARR September 2021 9 · Anonymous

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 Defense

Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer

2021-10-14 · EMNLP 2021 11 · Fanchao Qi, Yangyi Chen, Xurui Zhang, Mukai Li 외

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