# LipShiFT: A Certifiably Robust Shift-based Vision Transformer Source: [LipShiFT: A Certifiably Robust Shift-based Vision Transformer]() Collection index: [llms.txt]() Data updated: 2025-10-26T04:20:40.032Z Authors: Rohan Menon, Nicola Franco, Stephan G\\"unnemann Published: 2025-03-18T21:38:18.000Z ## Abstract Deriving tight Lipschitz bounds for transformer-based architectures presents a significant challenge. The large input sizes and high-dimensional attention modules typically prove to be crucial bottlenecks during the training process and leads to sub-optimal results. Our research highlights practical constraints of these methods in vision tasks. We find that Lipschitz-based margin training acts as a strong regularizer while restricting weights in successive layers of the model. Focusing on a Lipschitz continuous variant of the ShiftViT model, we address significant training challenges for transformer-based architectures under norm-constrained input setting. We provide an upper bound estimate for the Lipschitz constants of this model using the $l\_2$ norm on common image classification datasets. Ultimately, we demonstrate that our method scales to larger models and advances the state-of-the-art in certified robustness for transformer-based architectures. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()