An Optimal Control View of Adversarial Machine Learning
I describe an optimal control view of adversarial machine learning, where the dynamical system is the machine learner, the input are adversarial actions, and the control costs are defined by the adversary's goals to do harm and be hard to detect. This view encompasses many types of adversarial machine learning, including test-item attacks, training-data poisoning, and adversarial reward shaping. The view encourages adversarial machine learning researcher to utilize advances in control theory and reinforcement learning.
Code (0)
등록된 구현이 없습니다.
Tasks
BIG-bench Machine LearningData Poisoningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Adversarially Robust Neural Networks via Optimal Control: Bridging Robustness with Lyapunov Stability
Deep neural networks are known to be vulnerable to adversarial perturbations. In this paper, we bridge adversarial robustness of neural nets with Lyapunov stability of dynamical systems. From this viewpoint, training neu…
Adversarial RobustnessDeep Learning Theory Review: An Optimal Control and Dynamical Systems Perspective
Attempts from different disciplines to provide a fundamental understanding of deep learning have advanced rapidly in recent years, yet a unified framework remains relatively limited. In this article, we provide one possi…
Deep LearningLearning TheoryMeta-LearningA minimax optimal control approach for robust neural ODEs
In this paper, we address the adversarial training of neural ODEs from a robust control perspective. This is an alternative to the classical training via empirical risk minimization, and it is widely used to enforce reli…
DPAC: Distribution-Preserving Adversarial Control for Diffusion Sampling
Adversarially guided diffusion sampling often achieves the target class, but sample quality degrades as deviations between the adversarially controlled and nominal trajectories accumulate. We formalize this degradation a…
ARRTOC: Adversarially Robust Real-Time Optimization and Control
Real-Time Optimization (RTO) plays a crucial role in the process operation hierarchy by determining optimal set-points for the lower-level controllers. However, at the control layer, these set-points may be difficult to …