paper-with-me

Papers

Generating Black-Box Adversarial Examples for Text Classifiers Using a Deep Reinforced Model

2019-09-17 · Prashanth Vijayaraghavan, Deb Roy

Recently, generating adversarial examples has become an important means of measuring robustness of a deep learning model. Adversarial examples help us identify the susceptibilities of the model and further counter those vulnerabilities by applying adversarial training techniques. In natural language domain, small perturbations in the form of misspellings or paraphrases can drastically change the semantics of the text. We propose a reinforcement learning based approach towards generating adversarial examples in black-box settings. We demonstrate that our method is able to fool well-trained models for (a) IMDB sentiment classification task and (b) AG's news corpus news categorization task with significantly high success rates. We find that the adversarial examples generated are semantics-preserving perturbations to the original text.

📄 PDF Abstract BibTeX arXiv:1909.07873

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Sentiment AnalysisSentiment Classification

Similar Papers 제목 키워드 기반

DANCin SEQ2SEQ: Fooling Text Classifiers with Adversarial Text Example Generation

2017-12-14 · Catherine Wong

Machine learning models are powerful but fallible. Generating adversarial examples - inputs deliberately crafted to cause model misclassification or other errors - can yield important insight into model assumptions and v…

Adversarial TextReinforcement Learning

On the Role of Generalization in Transferability of Adversarial Examples

2022-06-18 · Yilin Wang, Farzan Farnia

Black-box adversarial attacks designing adversarial examples for unseen neural networks (NNs) have received great attention over the past years. While several successful black-box attack schemes have been proposed in the…

Generalization Bounds

ManiGen: A Manifold Aided Black-box Generator of Adversarial Examples

2020-07-11 · Guanxiong Liu, Issa Khalil, Abdallah Khreishah, Abdulelah Algosaibi 외

Machine learning models, especially neural network (NN) classifiers, have acceptable performance and accuracy that leads to their wide adoption in different aspects of our daily lives. The underlying assumption is that t…

Generating Natural Adversarial Examples

2017-10-31 · ICLR 2018 1 · Zhengli Zhao, Dheeru Dua, Sameer Singh

Due to their complex nature, it is hard to characterize the ways in which machine learning models can misbehave or be exploited when deployed. Recent work on adversarial examples, i.e. inputs with minor perturbations tha…

Adversarial Attackimage-classificationImage ClassificationMachine Translation+2

Blocking Transferability of Adversarial Examples in Black-Box Learning Systems

2017-03-13 · Hossein Hosseini, Yize Chen, Sreeram Kannan, Baosen Zhang 외

Advances in Machine Learning (ML) have led to its adoption as an integral component in many applications, including banking, medical diagnosis, and driverless cars. To further broaden the use of ML models, cloud-based se…

BlockingMedical Diagnosis