Deep Text Classification Can be Fooled

26 April 2017

Papers citing "Deep Text Classification Can be Fooled"

8 / 58 papers shown

Title
Discrete Adversarial Attacks and Submodular Optimization with Applications to Text Classification Qi Lei Lingfei Wu Pin-Yu Chen A. Dimakis Inderjit S. Dhillon Michael Witbrock AAML 15 92 0 01 Dec 2018
Evading classifiers in discrete domains with provable optimality guarantees B. Kulynych Jamie Hayes N. Samarin Carmela Troncoso AAML 13 19 0 25 Oct 2018
Attack Graph Convolutional Networks by Adding Fake Nodes Xiaoyun Wang Minhao Cheng Joe Eaton Cho-Jui Hsieh S. F. Wu AAML GNN 25 78 0 25 Oct 2018
Detecting egregious responses in neural sequence-to-sequence models Tianxing He James R. Glass AAML 21 22 0 11 Sep 2018
Adversarial Over-Sensitivity and Over-Stability Strategies for Dialogue Models Tong Niu Joey Tianyi Zhou AAML 21 85 0 06 Sep 2018
Adversarial Texts with Gradient Methods Zhitao Gong Wenlu Wang Yangqiu Song D. Song Wei-Shinn Ku AAML 20 77 0 22 Jan 2018
Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers Ji Gao Jack Lanchantin M. Soffa Yanjun Qi AAML 18 706 0 13 Jan 2018
Towards Crafting Text Adversarial Samples Suranjana Samanta S. Mehta AAML 14 219 0 10 Jul 2017