paper-with-me

Papers

Adversarial Examples for Model-Based Control: A Sensitivity Analysis

2022-07-14 · Po-han Li, Ufuk Topcu, Sandeep P. Chinchali

We propose a method to attack controllers that rely on external timeseries forecasts as task parameters. An adversary can manipulate the costs, states, and actions of the controllers by forging the timeseries, in this case perturbing the real timeseries. Since the controllers often encode safety requirements or energy limits in their costs and constraints, we refer to such manipulation as an adversarial attack. We show that different attacks on model-based controllers can increase control costs, activate constraints, or even make the control optimization problem infeasible. We use the linear quadratic regulator and convex model predictive controllers as examples of how adversarial attacks succeed and demonstrate the impact of adversarial attacks on a battery storage control task for power grid operators. As a result, our method increases control cost by $8500\%$ and energy constraints by $13\%$ on real electricity demand timeseries.

📄 PDF Abstract BibTeX arXiv:2207.06982

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial AttackSensitivity

Similar Papers 제목 키워드 기반

A Noise-Sensitivity-Analysis-Based Test Prioritization Technique for Deep Neural Networks

2019-01-01 · Long Zhang, Xuechao Sun, Yong Li, Zhen-Yu Zhang

Deep neural networks (DNNs) have been widely used in the fields such as natural language processing, computer vision and image recognition. But several studies have been shown that deep neural networks can be easily fool…

Sensitivity

Unveiling and Mitigating Adversarial Vulnerabilities in Iterative Optimizers

2025-04-26 · Elad Sofer, Tomer Shaked, Caroline Chaux, Nir Shlezinger

Machine learning (ML) models are often sensitive to carefully crafted yet seemingly unnoticeable perturbations. Such adversarial examples are considered to be a property of ML models, often associated with their black-bo…

Sensitivity

With False Friends Like These, Who Can Have Self-Knowledge?

2020-09-28 · Lue Tao, Songcan Chen

Adversarial examples arise from excessive sensitivity of a model. Commonly studied adversarial examples are malicious inputs, crafted by an adversary from correctly classified examples, to induce misclassification. This …

Sensitivity

Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations

2020-02-11 · ICML 2020 1 · Florian Tramèr, Jens Behrmann, Nicholas Carlini, Nicolas Papernot 외

Adversarial examples are malicious inputs crafted to induce misclassification. Commonly studied sensitivity-based adversarial examples introduce semantically-small changes to an input that result in a different model pre…

Sensitivity

Balanced Adversarial Training: Balancing Tradeoffs Between Oversensitivity and Undersensitivity in NLP Models

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Traditional (\emph{oversensitive}) adversarial examples involve finding a small perturbation that does not change an input's true label but confuses the classifier into outputting a different prediction. \emph{Undersensi…

Contrastive LearningNatural Language InferenceParaphrase Identification