This paper focuses on learning transferable adversarial examples specifically against defense models (models to defense adversarial attacks). In particular, we show that a simple …
A significant robustness gap exists between machine intelligence and human perception despite recent advances in deep learning. Deep learning is not provably secure. A critical …
TL Molloy, J Inga, M Flad, JJ Ford… - … on Automatic Control, 2019 - ieeexplore.ieee.org
We consider the problem of computing parameters of player cost functionals such that given state and control trajectories constitute an open-loop Nash equilibrium for a noncooperative …
In this paper, we propose a gamification approach as a novel framework for smart building infrastructure with the goal of motivating human occupants to reconsider personal energy …
Energy game-theoretic frameworks have emerged to be a successful strategy to encourage energy efficient behavior in large scale by leveraging human-in-the-loop strategy. A number …
We study the expressibility and learnability of solution functions of convex optimization and their multi-layer architectural extension. The main results are:(1) the class of solution …
A Neufeld, MNC En, Y Zhang - arXiv preprint arXiv:2403.09532, 2024 - arxiv.org
In this paper we develop a Stochastic Gradient Langevin Dynamics (SGLD) algorithm tailored for solving a certain class of non-convex distributionally robust optimisation …
Digital forensics plays a crucial role in identifying, analysing, and presenting cyber threats as evidence in a court of law. Artificial intelligence, particularly machine learning and deep …
This chapter summarizes the game theoretical strategies for generating adversarial manipulations. The adversarial learning objective for our adversaries is assumed to be to …