Corrupting the When and What: Differentiable Adversarial Attacks for Continuous Time Event Sequences

Continuous-Time Event Sequences (CTESs) are discrete events occurring at irregular times along a continuous timeline and are common in domains such as healthcare and finance. Marked Temporal Point Processes (MTPPs) model CTESs by capturing both event timing and type. While widely used, adversarial evaluation and attacks on MTPPs remain largely unexplored. In this work, we propose adversarial attacks specifically designed for MTPP models. A key requirement for effective adversarial attacks is imperceptibility, i.e., the perturbations should remain subtle or undetectable. While in domains such as images or text this is typically enforced by constraining perturbations within a fixed \(L_{p}\) norm ball, applying similar constraints to CTESs is non-trivial due to their sequential nature and variability in time scales and sequence lengths. To address this challenge, we first permute the events and then introduce additive noise to the arrival timestamps. However, finding the worst-case adversarial example under this setting becomes a hard combinatorial problem, involving a search over a factorially large permutation space. To overcome this, we introduce a novel differentiable framework,