Provable Robustness for Streaming Models with a Sliding Window
Not on the map. Why?
Abstract (arXiv)
The literature on provable robustness in machine learning has primarily focused on static prediction problems, such as image classification, in which input samples are assumed to be independent and model performance is measured as an expectation over the input distribution. Robustness certificates are derived for individual input instances with the assumption that the model is evaluated on each instance separately. However, in many deep learning applications such as online content recommendation and stock market analysis, models use historical data to make predictions. Robustness certificates based on the assumption of independent input samples are not directly applicable in such scenarios. In this work, we focus on the provable robustness of machine learning models in the context of data streams, where inputs are presented as a sequence of potentially correlated items. We derive robustness certificates for models that use a fixed-size sliding window over the input stream. Our guarantees hold for the average model performance across the entire stream and are independent of stream size, making them suitable for large data streams. We perform experiments on speech detection and human activity recognition tasks and show that our certificates can produce meaningful performance guarantees against adversarial perturbations.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 53 of its 75 references that are in the map. First posted on arXiv 28 Mar 2023.
Builds on
53 of 75 references.
References · 53
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2013Intriguing properties of neural networkscited by 5,114
- 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
- 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
- 2016End to End Learning for Self-Driving Carscited by 1,000
- 2016Adversarial Machine Learning at Scalecited by 934
- 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 741
- 2017Evasion Attacks against Machine Learning at Test Timecited by 686
- 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
- 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
- 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
38 more
- 2017Countering Adversarial Images using Input Transformationscited by 517
- 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
- 2019Provably Robust Deep Learning via Adversarially Trained Smoothed Classifierscited by 328
- 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 322
- 2017Adversarial Attacks on Neural Network Policiescited by 314
- 2018Adversarial Risk and the Dangers of Evaluating Against Weak Attackscited by 221
- 2019Adversarial Policies: Attacking Deep Reinforcement Learningcited by 209
- 2017Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Artcited by 182
- 2017On the (Statistical) Detection of Adversarial Examplescited by 180
- 2018Certified Adversarial Robustness with Additive Noisecited by 178
- 2018Semidefinite relaxations for certifying robustness to adversarial examplescited by 178
- 2018Stochastic Activation Pruning for Robust Adversarial Defensecited by 171
- 2017Robust Deep Reinforcement Learning with Adversarial Attackscited by 152
- 2016End-to-end Learning of Driving Models from Large-scale Video Datasetscited by 147
- 2021Robust Reinforcement Learning on State Observations with Learned Optimal Adversarycited by 133
- 2020Certified Defenses for Adversarial Patchescited by 100
- 2017Vulnerability of Deep Reinforcement Learning to Policy Induction Attackscited by 91
- 2020Deep Learning for Financial Applications : A Surveycited by 90
- 2019Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagationcited by 87
- 2016Adversarial Examples Detection in Deep Networks with Convolutional Filter Statisticscited by 77
- 2016Very Deep Convolutional Neural Networks for Raw Waveformscited by 68
- 2020Robust Reinforcement Learning using Adversarial Populationscited by 64
- 2020Curse of Dimensionality on Randomized Smoothing for Certifiable Robustnesscited by 56
- 2017Adversarial and Clean Data Are Not Twinscited by 52
- 2018Training verified learners with learned verifierscited by 50
- 2020Robust Reinforcement Learning via Adversarial training with Langevin Dynamicscited by 45
- 2021CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothingcited by 41
- 2022Provable Reinforcement Learning with a Short-Term Memorycited by 40
- 2020Second-Order Provable Defenses against Adversarial Attackscited by 39
- 2021Improved, Deterministic Smoothing for L_1 Certified Robustnesscited by 39
- 2021Policy Smoothing for Provably Robust Reinforcement Learningcited by 39
- 2018Scene-Aware Audio for 360textdegree Videoscited by 25
- 2020A Framework for Adversarially Robust Streaming Algorithmscited by 21
- 2019The Adversarial Robustness of Samplingcited by 18
- 2021Center Smoothing: Certified Robustness for Networks with Structured Outputscited by 18
- 2017Streaming Robust Submodular Maximization: A Partitioned Thresholding Approachcited by 13
- 2021Adversarial Robustness of Streaming Algorithms through Importance Samplingcited by 13
- 2020Online Automatic Speech Recognition with Listen, Attend and Spell Modelcited by 10
50 most cited of 53 All 53 (JSON)
Built on by
Citing papers per year: 2023: 1.
1 paper.
- 2023Certifying LLM Safety against Adversarial Promptingcited by 248
- 2023Certifying LLM Safety against Adversarial Prompting6 Sep 2023