Online Evasion Attacks on Recurrent Models:The Power of Hallucinating the Future
Not on the map. Why?
Abstract (arXiv)
Recurrent models are frequently being used in online tasks such as autonomous driving, and a comprehensive study of their vulnerability is called for. Existing research is limited in generality only addressing application-specific vulnerability or making implausible assumptions such as the knowledge of future input. In this paper, we present a general attack framework for online tasks incorporating the unique constraints of the online setting different from offline tasks. Our framework is versatile in that it covers time-varying adversarial objectives and various optimization constraints, allowing for a comprehensive study of robustness. Using the framework, we also present a novel white-box attack called Predictive Attack that `hallucinates' the future. The attack achieves 98 percent of the performance of the ideal but infeasible clairvoyant attack on average. We validate the effectiveness of the proposed framework and attacks through various experiments.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 14 of its 30 references that are in the map. First posted on arXiv 8 Jul 2022.
Builds on
14 of 30 references.
References · 14
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2013Intriguing properties of neural networkscited by 5,155
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
- 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
- 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 721
- 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 536
- 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 334
- 2017Multitask learning and benchmarking with clinical time series datacited by 290
- 2019Adversarial Attacks on Deep Neural Networks for Time Series Classificationcited by 53
- 2020Real-time, Universal, and Robust Adversarial Attacks Against Speaker Recognition Systemscited by 26
- 2018Adversarial Attacks on Variational Autoencoderscited by 19
2 more
- 2020Adversarial Attacks on Probabilistic Autoregressive Forecasting Modelscited by 13
- 2019Real-Time Adversarial Attackscited by 11
Built on by
Citing papers per year: 2026: 1.
1 paper.