Related papers: Distributed watermarking for secure control of mic…

As the quality of image generators continues to improve, deepfakes become a topic of considerable societal debate. Image watermarking allows responsible model owners to detect and label their AI-generated content, which can mitigate the…

Distributed secondary control plays an important role in DC microgrids, since it ensures system control objectives, which are power sharing and DC bus voltage stability. Previous studies have suggested using a control architecture that…

The increasing integration of IoT-connected devices in smart grids has introduced new vulnerabilities at the distribution level. Of particular concern is the potential for cyberattacks that exploit high-wattage IoT devices, such as EV…

The commercialization of deep learning creates a compelling need for intellectual property (IP) protection. Deep neural network (DNN) watermarking has been proposed as a promising tool to help model owners prove ownership and fight piracy.…

We propose an online framework to detect cyber attacks on Automatic Generation Control (AGC). A cyber at- tack detection algorithm is designed based on the approach of Dynamic Watermarking. The detection algorithm provides a theoretical…

We consider the problem of stabilizing voltages in DC microGrids (mGs) given by the interconnection of Distributed Generation Units (DGUs), power lines and loads. We propose a decentralized control architecture where the primary controller…

Watermarking is one of the most important copyright protection tools for digital media. The most challenging type of watermarking is the imperceptible one, which embeds identifying information in the data while retaining the latter's…

Integrating watermarking into the generation process of latent diffusion models (LDMs) simplifies detection and attribution of generated content. Semantic watermarks, such as Tree-Rings and Gaussian Shading, represent a novel class of…

Power grids worldwide are increasingly victims of cyberattacks, where attackers can cause immense damage to critical infrastructure. The growing digitalization and networking in power grids combined with insufficient protection against…

Appropriate control of high penetration renewable energies in power systems requires a complete modeling of the system. In this paper, a comprehensive state space modeling of voltage source inverters, networks and loads are studied. We have…

In this work, we present new secondary regulators for current sharing and voltage balancing in DC microgrids, composed of distributed generation units, dynamic RLC lines, and nonlinear ZIP (constant impedance, constant current, and constant…

Deep neural networks (DNNs) have demonstrated their superiority in practice. Arguably, the rapid development of DNNs is largely benefited from high-quality (open-sourced) datasets, based on which researchers and developers can easily…

As deep learning (DL) models are widely and effectively used in Machine Learning as a Service (MLaaS) platforms, there is a rapidly growing interest in DL watermarking techniques that can be used to confirm the ownership of a particular…

Diffusion Models (DMs) have shown remarkable capabilities in various image-generation tasks. However, there are growing concerns that DMs could be used to imitate unauthorized creations and thus raise copyright issues. To address this…

Power grids heavily rely on Automatic Generation Control (AGC) systems to maintain grid stability by balancing generation and demand. However, the increasing digitization and interconnection of power grid infrastructure expose AGC systems…

Machine learning is increasingly used in security-critical applications, such as autonomous driving, face recognition and malware detection. Most learning methods, however, have not been designed with security in mind and thus are…

Microgrids (MGs) rely on networked control supported by off-the-shelf wireless communications. This makes them vulnerable to cyber-attacks, such as denial-of-service (DoS). In this paper, we mitigate those attacks by applying the concepts…

We propose dgMARK, a decoding-guided watermarking method for discrete diffusion language models (dLLMs). Unlike autoregressive models, dLLMs can generate tokens in arbitrary order. While an ideal conditional predictor would be invariant to…

To trace the copyright of deep neural networks, an owner can embed its identity information into its model as a watermark. The capacity of the watermark quantify the maximal volume of information that can be verified from the watermarked…

In this paper, we introduce a simple yet effective tabular data watermarking mechanism with statistical guarantees. We show theoretically that the proposed watermark can be effectively detected, while faithfully preserving the data…