paper-with-me

홈 › Papers

Data-Driven Control and Data-Poisoning attacks in Buildings: the KTH Live-In Lab case study

2021-03-10 · Alessio Russo, Marco Molinari, Alexandre Proutiere

This work investigates the feasibility of using input-output data-driven control techniques for building control and their susceptibility to data-poisoning techniques. The analysis is performed on a digital replica of the KTH Livein Lab, a non-linear validated model representing one of the KTH Live-in Lab building testbeds. This work is motivated by recent trends showing a surge of interest in using data-based techniques to control cyber-physical systems. We also analyze the susceptibility of these controllers to data-poisoning methods, a particular type of machine learning threat geared towards finding imperceptible attacks that can undermine the performance of the system under consideration. We consider the Virtual Reference Feedback Tuning (VRFT), a popular data-driven control technique, and show its performance on the KTH Live-In Lab digital replica. We then demonstrate how poisoning attacks can be crafted and illustrate the impact of such attacks. Numerical experiments reveal the feasibility of using data-driven control methods for finding efficient control laws. However, a subtle change in the datasets can significantly deteriorate the performance of VRFT.

📄 PDF Abstract BibTeX arXiv:2103.06208

Code (0)

등록된 구현이 없습니다.

Tasks

Data Poisoning

Similar Papers 제목 키워드 기반

Analysis and Detectability of Offline Data Poisoning Attacks on Linear Dynamical Systems

2022-11-16 · Alessio Russo

In recent years, there has been a growing interest in the effects of data poisoning attacks on data-driven control methods. Poisoning attacks are well-known to the Machine Learning community, which, however, make use of …

Data Poisoning

Online Poisoning Attacks Against Data-Driven Predictive Control

2022-09-19 · Yue Yu, Ruihan Zhao, Sandeep Chinchali, Ufuk Topcu

Data-driven predictive control (DPC) is a feedback control method for systems with unknown dynamics. It repeatedly optimizes a system's future trajectories based on past input-output data. We develop a numerical method t…

Poisoning Attacks against Data-Driven Control Methods

2021-03-10 · Alessio Russo, Alexandre Proutiere

This paper investigates poisoning attacks against data-driven control methods. This work is motivated by recent trends showing that, in supervised learning, slightly modifying the data in a malicious manner can drastical…

LEMMA

Cordyceps: Covert Control Attacks on LLMs via Data Poisoning

2026-05-26 · Zedian Shao, Charles Fleming, Teodora Baluta arxiv

Large language models (LLMs) are often fine-tuned on uncurated text datasets that adversaries can poison. Existing poisoning attacks primarily rely on fixed trigger phrases that defenses such as outlier detection, clean-…

Outlier Detection

Model-Targeted Poisoning Attacks with Provable Convergence

2020-06-30 · Fnu Suya, Saeed Mahloujifar, Anshuman Suri, David Evans 외

In a poisoning attack, an adversary with control over a small fraction of the training data attempts to select that data in a way that induces a corrupted model that misbehaves in favor of the adversary. We consider pois…

model