Timezone: »
The vulnerability to adversarial attacks has been a critical issue for deep neural networks. Addressing this issue requires a reliable way to evaluate the robustness of a network. Recently, several methods have been developed to compute robustness quantification for neural networks, namely, certified lower bounds of the minimum adversarial perturbation. Such methods, however, were devised for feed-forward networks, e.g. multi-layer perceptron or convolutional networks. It remains an open problem to quantify robustness for recurrent networks, especially LSTM and GRU. For such networks, there exist additional challenges in computing the robustness quantification, such as handling the inputs at multiple steps and the interaction between gates and states. In this work, we propose POPQORN (Propagated-output Quantified Robustness for RNNs), a general algorithm to quantify robustness of RNNs, including vanilla RNNs, LSTMs, and GRUs. We demonstrate its effectiveness on different network architectures and show that the robustness quantification on individual steps can lead to new insights.
Author Information
CHING-YUN KO (The University of Hong Kong)
Zhaoyang Lyu (The Chinese University of Hong Kong)
Tsui-Wei Weng (MIT)
Luca Daniel (Massachusetts Institute of Technology)
Ngai Wong (The University of Hong Kong)
Dahua Lin (The Chinese University of Hong Kong)
Related Events (a corresponding poster, oral, or spotlight)
-
2019 Oral: POPQORN: Quantifying Robustness of Recurrent Neural Networks »
Tue. Jun 11th 07:00 -- 07:05 PM Room Grand Ballroom
More from the Same Authors
-
2022 : Fast Convergence for Unstable Reinforcement Learning Problems by Logarithmic Mapping »
Wang Zhang · Lam Nguyen · Subhro Das · Alexandre Megretsky · Luca Daniel · Tsui-Wei Weng -
2023 : On Robustness-Accuracy Characterization of Large Language Models using Synthetic Datasets »
Ching-Yun (Irene) Ko · Pin-Yu Chen · Payel Das · Yung-Sung Chuang · Luca Daniel -
2023 : On Robustness-Accuracy Characterization of Large Language Models using Synthetic Datasets »
Ching-Yun (Irene) Ko · Pin-Yu Chen · Payel Das · Yung-Sung Chuang · Luca Daniel -
2023 Poster: ConCerNet: A Contrastive Learning Based Framework for Automated Conservation Law Discovery and Trustworthy Dynamical System Prediction »
Wang Zhang · Lily Weng · Subhro Das · Alexandre Megretsky · Luca Daniel · Lam Nguyen -
2022 Poster: Revisiting Contrastive Learning through the Lens of Neighborhood Component Analysis: an Integrated Framework »
Ching-Yun (Irene) Ko · Jeet Mohapatra · Sijia Liu · Pin-Yu Chen · Luca Daniel · Lily Weng -
2022 Spotlight: Revisiting Contrastive Learning through the Lens of Neighborhood Component Analysis: an Integrated Framework »
Ching-Yun (Irene) Ko · Jeet Mohapatra · Sijia Liu · Pin-Yu Chen · Luca Daniel · Lily Weng -
2020 Poster: Neural Network Control Policy Verification With Persistent Adversarial Perturbation »
Yuh-Shyang Wang · Tsui-Wei Weng · Luca Daniel -
2020 Poster: Proper Network Interpretability Helps Adversarial Robustness in Classification »
Akhilan Boopathy · Sijia Liu · Gaoyuan Zhang · Cynthia Liu · Pin-Yu Chen · Shiyu Chang · Luca Daniel -
2019 Poster: PROVEN: Verifying Robustness of Neural Networks with a Probabilistic Approach »
Tsui-Wei Weng · Pin-Yu Chen · Lam Nguyen · Mark Squillante · Akhilan Boopathy · Ivan Oseledets · Luca Daniel -
2019 Oral: PROVEN: Verifying Robustness of Neural Networks with a Probabilistic Approach »
Tsui-Wei Weng · Pin-Yu Chen · Lam Nguyen · Mark Squillante · Akhilan Boopathy · Ivan Oseledets · Luca Daniel -
2018 Poster: Towards Fast Computation of Certified Robustness for ReLU Networks »
Tsui-Wei Weng · Huan Zhang · Hongge Chen · Zhao Song · Cho-Jui Hsieh · Luca Daniel · Duane Boning · Inderjit Dhillon -
2018 Oral: Towards Fast Computation of Certified Robustness for ReLU Networks »
Tsui-Wei Weng · Huan Zhang · Hongge Chen · Zhao Song · Cho-Jui Hsieh · Luca Daniel · Duane Boning · Inderjit Dhillon