Fine-grained Local Sensitivity Analysis of Standard Dot-Product Self-Attention

Self-attention has been widely used in various machine learning models, such as vision transformers. The standard dot-product self-attention is arguably the most popular structure, and there is a growing interest in understanding the mathematical properties of such attention mechanisms. This paper presents a fine-grained local sensitivity analysis of the standard dot-product selfattention, leading to new non-vacuous certified robustness results for vision transformers. Despite the well-known fact that dot-product selfattention is not (globally) Lipschitz, we develop new theoretical analysis of Local Fine-grained Attention Sensitivity (LoFAST) quantifying the effect of input feature perturbations on the attention output. Our analysis reveals that the local sensitivity of dot-product self-attention to ℓ 2 perturbations can actually be controlled by several key quantities associated with the attention weight matrices and the unperturbed input. We empirically validate our theoretical findings by computing non-vacuous certified ℓ 2 -robustness for vision transformers on CIFAR-10 and SVHN datasets. The code for LoFAST is available at https: //github.com/AaronHavens/LoFAST .