We introduce path-sampled integrated gradients (PS-IG), a framework that generalizes feature attribution by computing the expected value over baselines sampled along the linear interpolation path. We prove that PS-IG is mathematically equivalent to path-weighted integrated gradients, provided the weighting function matches the cumulative distribution function of the sampling density. This equivalence allows the stochastic expectation to be evaluated via a deterministic Riemann sum, improving the error convergence rate from $O(m^{-1/2})$ to $O(m^{-1})$ for smooth models. Furthermore, we demonstrate analytically that PS-IG functions as a variance-reducing filter against gradient noise - strictly lowering attribution variance by a factor of 1/3 under uniform sampling - while preserving key axiomatic properties such as linearity and implementation invariance.

Chances are you already have an established process for identifying attackers and blocking external threats. You've taken steps to reduce the likelihood of an attack by exercising good cyber hygiene and following key identity and access management (IAM) best practices, such as adhering to the principle of least privilege. An insider threat is when an insider's credentials and access are used, either deliberately by malicious actors or indirectly by criminals with stolen or acquired credentials, to illicitly obtain sensitive data from an organization. According to a recent SANS survey, 76 percent of security professionals ranked malicious, accidental or negligent insiders as the most damaging threat vector they face. Insiders all look the same, making them increasingly difficult to detect.