Building Resilient AI: Strengthening Data, Security, and Robustness in Neural Networks

Data quality is fundamental to machine-learning performance. An understanding of the data distribution directly influences model security and robustness. By analyzing the curvature of the loss landscape with respect to data, we can detect regions of the distribution that are well represented, and samples which are under-represented. Samples in these under-represented “tails” are disproportionately sensitive to hardware and adversarial noise and are therefore less robust. Compounding the problem, models tend to memorize these rare examples, increasing privacy risk. Curvature analysis helps expose such vulnerabilities by powering stronger membership-inference attacks. Synthetic-data techniques such as DP-ImySyn [24] can be used to augment scarce data, strengthening coverage. Ultimately, building resilient, robust, and secure models begins with understanding the data and fortifying its weak points.