paper-with-me

홈 › Papers

AdvCodeMix: Adversarial Attack on Code-Mixed Data

2021-10-30 · Sourya Dipta Das, Ayan Basak, Soumil Mandal, Dipankar Das

Research on adversarial attacks are becoming widely popular in the recent years. One of the unexplored areas where prior research is lacking is the effect of adversarial attacks on code-mixed data. Therefore, in the present work, we have explained the first generalized framework on text perturbation to attack code-mixed classification models in a black-box setting. We rely on various perturbation techniques that preserve the semantic structures of the sentences and also obscure the attacks from the perception of a human user. The present methodology leverages the importance of a token to decide where to attack by employing various perturbation strategies. We test our strategies on various sentiment classification models trained on Bengali-English and Hindi-English code-mixed datasets, and reduce their F1-scores by nearly 51 % and 53 % respectively, which can be further reduced if a larger number of tokens are perturbed in a given sentence.

📄 PDF Abstract BibTeX arXiv:2111.00350

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial AttackSentenceSentiment AnalysisSentiment Classification

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

BeamAttack: Generating High-quality Textual Adversarial Examples through Beam Search and Mixed Semantic Spaces

2023-03-09 · Hai Zhu, Qingyang Zhao, Yuren Wu

Natural language processing models based on neural networks are vulnerable to adversarial examples. These adversarial examples are imperceptible to human readers but can mislead models to make the wrong predictions. In a…

Heuristic Search

Towards Generating Adversarial Examples on Mixed-type Data

2022-10-17 · Han Xu, Menghai Pan, Zhimeng Jiang, Huiyuan Chen 외

The existence of adversarial attacks (or adversarial examples) brings huge concern about the machine learning (ML) model's safety issues. For many safety-critical ML tasks, such as financial forecasting, fraudulent detec…

Anomaly DetectionVocal Bursts Type Prediction

Elevating Code-mixed Text Handling through Auditory Information of Words

2023-10-27 · Mamta, Zishan Ahmad, Asif Ekbal

With the growing popularity of code-mixed data, there is an increasing need for better handling of this type of data, which poses a number of challenges, such as dealing with spelling variations, multiple languages, diff…

Language ModelingLanguage Modelling

Availability Adversarial Attack and Countermeasures for Deep Learning-based Load Forecasting

2023-01-04 · Wangkun Xu, Fei Teng

The forecast of electrical loads is essential for the planning and operation of the power system. Recently, advances in deep learning have enabled more accurate forecasts. However, deep neural networks are prone to adver…

Adversarial AttackLoad ForecastingPosition

Game Theoretic Mixed Experts for Combinational Adversarial Machine Learning

2022-11-26 · Ethan Rathbun, Kaleel Mahmood, Sohaib Ahmad, Caiwen Ding 외

Recent advances in adversarial machine learning have shown that defenses considered to be robust are actually susceptible to adversarial attacks which are specifically customized to target their weaknesses. These defense…

Adversarial Defense