Provable Robustness for Streaming Models with a Sliding Window
Kumar, Aounon, Sadasivan, Vinu Sankar, Feizi, Soheil
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Mar-28-2023
- Country:
- Africa > Ethiopia (0.04)
- North America
- United States
- Texas > Dallas County
- Dallas (0.04)
- Oregon > Multnomah County
- Portland (0.04)
- New York > New York County
- New York City (0.04)
- Massachusetts > Suffolk County
- Boston (0.04)
- Maryland
- Prince George's County > College Park (0.04)
- Baltimore (0.04)
- Hawaii > Honolulu County
- Honolulu (0.04)
- California
- San Francisco County > San Francisco (0.14)
- Los Angeles County > Long Beach (0.14)
- San Diego County > San Diego (0.04)
- Texas > Dallas County
- Canada
- United States
- Europe
- Asia
- China > Hong Kong (0.04)
- Russia > Siberian Federal District
- Novosibirsk Oblast > Novosibirsk (0.04)
- Genre:
- Research Report (0.82)
- Industry:
- Information Technology (1.00)
- Health & Medicine (1.00)
- Banking & Finance > Trading (1.00)
- Technology: