3 papers
cs.LG2026
Hierarchical End-to-End Taylor Bounds for Complete Neural Network Verification
Taha Entesari, Mahyar Fazlyab
Reachability analysis of neural networks, which seeks to compute or bound the set of outputs attainable over a given input domain, is central to certifying safety and robustness in…
cs.CL2025
Constrained Entropic Unlearning: A Primal-Dual Framework for Large Language Models
Taha Entesari, Arman Hatami, Rinat Khaziev +2
Large Language Models (LLMs) deployed in real-world settings increasingly face the need to unlearn sensitive, outdated, or proprietary information. Existing unlearning methods typi…
cs.LG2025
Certified Robustness via Dynamic Margin Maximization and Improved Lipschitz Regularization
Mahyar Fazlyab, Taha Entesari, Aniket Roy +1
To improve the robustness of deep classifiers against adversarial perturbations, many approaches have been proposed, such as designing new architectures with better robustness prop…