paper-with-me

Papers

Adversarial Attacks to Direct Data-driven Control for Destabilization

2023-03-13 · Hampei Sasahara

This study investigates the vulnerability of direct data-driven control to adversarial attacks in the form of a small but sophisticated perturbation added to the original data. The directed gradient sign method (DGSM) is developed as a specific attack method, based on the fast gradient sign method (FGSM), which has originally been considered in image classification. DGSM uses the gradient of the eigenvalues of the resulting closed-loop system and crafts a perturbation in the direction where the system becomes less stable. It is demonstrated that the system can be destabilized by the attack, even if the original closed-loop system with the clean data has a large margin of stability. To increase the robustness against the attack, regularization methods that have been developed to deal with random disturbances are considered. Their effectiveness is evaluated by numerical experiments using an inverted pendulum model.

📄 PDF Abstract BibTeX arXiv:2303.06837

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classification

Similar Papers 제목 키워드 기반

Robustifying Reinforcement Learning Agents via Action Space Adversarial Training

2020-07-14 · Kai Liang Tan, Yasaman Esfandiari, Xian Yeow Lee, Aakanksha 외

Adoption of machine learning (ML)-enabled cyber-physical systems (CPS) are becoming prevalent in various sectors of modern society such as transportation, industrial, and power grids. Recent studies in deep reinforcement…

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Practical Adversarial Attacks Against AI-Driven Power Allocation in a Distributed MIMO Network

2023-01-23 · Ömer Faruk Tuna, Fehmi Emre Kadan, Leyli Karaçay

In distributed multiple-input multiple-output (D-MIMO) networks, power control is crucial to optimize the spectral efficiencies of users and max-min fairness (MMF) power control is a commonly used strategy as it satisfie…

Fairness

Stability Via Adversarial Training of Neural Network Stochastic Control of Mean-Field Type

2022-09-27 · Julian Barreiro-Gomez, Salah Eddine Choutri, Boualem Djehiche

In this paper, we present an approach to neural network mean-field-type control and its stochastic stability analysis by means of adversarial inputs (aka adversarial attacks). This is a class of data-driven mean-field-ty…

Vocal Bursts Type Prediction

DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models

2026-05-15 · Ye Sun, Xin Wang, Jiaming Zhang, Yifeng Gao 외 arxiv

While vision and multimodal foundation models underpin critical tasks from perception to complex reasoning, they remain highly vulnerable to adversarial attacks. However, traditional adversarial attacks are typically lim…

A Practical Adversarial Attack on Contingency Detection of Smart Energy Systems

2021-09-13 · Moein Sabounchi, Jin Wei-Kocsis

Due to the advances in computing and sensing, deep learning (DL) has widely been applied in smart energy systems (SESs). These DL-based solutions have proved their potentials in improving the effectiveness and adaptivene…

Adversarial AttackDeep Reinforcement LearningReinforcement Learning (RL)