arXiv subjects

Jinyuan Stella Sun

Publications and source records attributed to Jinyuan Stella Sun.

13 recordsLinked to original sources

arXiv2026

IntraShuffler: A Privacy Preserving Framework for Heterogeneous DP Federated Learning

Heterogeneous Differential Privacy (HDP) in Federated Learning (FL) allows clients to select individual privacy budgets ($\varepsilon_i$) according to institutional policies and data sensitivity. In practice, many HDP-FL systems employ $\varepsilon$-aware server aggregation to improve model utility by re-weighting client updates according to their declared privacy budgets. However, gradient updates in FL retain structural patterns induced by non-independent and identically-distributed (non-IID) data, and these additional signals exposed by $\varepsilon$-aware aggregation create new opportunities for inference by an honest-but-curious server. In this work, we first show that a server equipped with gradient denoising and surrogate modeling can mount a \emph{Privacy Inference Attack} that infers distributional attributes of clients and links updates from the same client across training rounds, measured via surrogate inference accuracy and linkage success, under realistic knowledge constraints. The Shuffle-Model has been widely studied as a defense against such inference risks by anonymizing update sources, but it is fundamentally incompatible with HDP-FL $\varepsilon$-aware aggregation. To address this challenge, we propose \textbf{IntraShuffler}, a middleware defense framework designed for HDP-FL systems. IntraShuffler introduces a privacy-aware shuffling mechanism that groups clients into privacy-compatible buckets and performs parameter-level shuffling within each bucket to disrupt persistent gradient structure while preserving $\varepsilon$-aware aggregation. Experiments across four different datasets show that IntraShuffler reduces gradient recoverability by over 60% and decreases surrogate inference accuracy from 0.78 to 0.33 while maintaining comparable model utility across multiple FL aggregation rules.

cs.LG↗

arXiv2025

Accuracy is Not Enough: Poisoning Interpretability in Federated Learning via Color Skew

As machine learning models are increasingly deployed in safety-critical domains, visual explanation techniques have become essential tools for supporting transparency. In this work, we reveal a new class of attacks that compromise model interpretability without affecting accuracy. Specifically, we show that small color perturbations applied by adversarial clients in a federated learning setting can shift a model's saliency maps away from semantically meaningful regions while keeping the prediction unchanged. The proposed saliency-aware attack framework, called Chromatic Perturbation Module, systematically crafts adversarial examples by altering the color contrast between foreground and background in a way that disrupts explanation fidelity. These perturbations accumulate across training rounds, poisoning the global model's internal feature attributions in a stealthy and persistent manner. Our findings challenge a common assumption in model auditing that correct predictions imply faithful explanations and demonstrate that interpretability itself can be an attack surface. We evaluate this vulnerability across multiple datasets and show that standard training pipelines are insufficient to detect or mitigate explanation degradation, especially in the federated learning setting, where subtle color perturbations are harder to discern. Our attack reduces peak activation overlap in Grad-CAM explanations by up to 35% while preserving classification accuracy above 96% on all evaluated datasets.

cs.CV↗

arXiv2025

Mitigating Adversarial Effects of False Data Injection Attacks in Power Grid

Deep Neural Networks have proven to be highly accurate at a variety of tasks in recent years. The benefits of Deep Neural Networks have also been embraced in power grids to detect False Data Injection Attacks (FDIA) while conducting critical tasks like state estimation. However, the vulnerabilities of DNNs along with the distinct infrastructure of the cyber-physical-system (CPS) can favor the attackers to bypass the detection mechanism. Moreover, the divergent nature of CPS engenders limitations to the conventional defense mechanisms for False Data Injection Attacks. In this paper, we propose a DNN framework with an additional layer that utilizes randomization to mitigate the adversarial effect by padding the inputs. The primary advantage of our method is when deployed to a DNN model it has a trivial impact on the model's performance even with larger padding sizes. We demonstrate the favorable outcome of the framework through simulation using the IEEE 14-bus, 30-bus, 118-bus, and 300-bus systems. Furthermore to justify the framework we select attack techniques that generate subtle adversarial examples that can bypass the detection mechanism effortlessly.

cs.CR↗

arXiv2024

Effects of Real-Life Traffic Sign Alteration on YOLOv7- an Object Recognition Model

The widespread adoption of Image Processing has propelled Object Recognition (OR) models into essential roles across various applications, demonstrating the power of AI and enabling crucial services. Among the applications, traffic sign recognition stands out as a popular research topic, given its critical significance in the development of autonomous vehicles. Despite their significance, real-world challenges, such as alterations to traffic signs, can negatively impact the performance of OR models. This study investigates the influence of altered traffic signs on the accuracy and effectiveness of object recognition, employing a publicly available dataset to introduce alterations in shape, color, content, visibility, angles and background. Focusing on the YOLOv7 (You Only Look Once) model, the study demonstrates a notable decline in detection and classification accuracy when confronted with traffic signs in unusual conditions including the altered traffic signs. Notably, the alterations explored in this study are benign examples and do not involve algorithms used for generating adversarial machine learning samples. This study highlights the significance of enhancing the robustness of object detection models in real-life scenarios and the need for further investigation in this area to improve their accuracy and reliability.

cs.CV↗

arXiv2024

Smart Driver Monitoring Robotic System to Enhance Road Safety : A Comprehensive Review

The future of transportation is being shaped by technology, and one revolutionary step in improving road safety is the incorporation of robotic systems into driver monitoring infrastructure. This literature review explores the current landscape of driver monitoring systems, ranging from traditional physiological parameter monitoring to advanced technologies such as facial recognition to steering analysis. Exploring the challenges faced by existing systems, the review then investigates the integration of robots as intelligent entities within this framework. These robotic systems, equipped with artificial intelligence and sophisticated sensors, not only monitor but actively engage with the driver, addressing cognitive and emotional states in real-time. The synthesis of existing research reveals a dynamic interplay between human and machine, offering promising avenues for innovation in adaptive, personalized, and ethically responsible human-robot interactions for driver monitoring. This review establishes a groundwork for comprehending the intricacies and potential avenues within this dynamic field. It encourages further investigation and advancement at the intersection of human-robot interaction and automotive safety, introducing a novel direction. This involves various sections detailing technological enhancements that can be integrated to propose an innovative and improved driver monitoring system.

cs.RO↗

arXiv2023

Towards Adversarial-Resilient Deep Neural Networks for False Data Injection Attack Detection in Power Grids

False data injection attacks (FDIAs) pose a significant security threat to power system state estimation. To detect such attacks, recent studies have proposed machine learning (ML) techniques, particularly deep neural networks (DNNs). However, most of these methods fail to account for the risk posed by adversarial measurements, which can compromise the reliability of DNNs in various ML applications. In this paper, we present a DNN-based FDIA detection approach that is resilient to adversarial attacks. We first analyze several adversarial defense mechanisms used in computer vision and show their inherent limitations in FDIA detection. We then propose an adversarial-resilient DNN detection framework for FDIA that incorporates random input padding in both the training and inference phases. Our simulations, based on an IEEE standard power system, demonstrate that this framework significantly reduces the effectiveness of adversarial attacks while having a negligible impact on the DNNs' detection performance.

cs.CR↗

arXiv2023

Graph Neural Network Framework for Security Assessment Informed by Topological Measures

In the power system, security assessment (SA) plays a pivotal role in determining the safe operation in a normal situation and some contingencies scenarios. Electrical variables as input variables of the model are mainly considered to indicate the power system operation as secure or insecure, according to the reliability criteria for contingency scenarios. In this approach, the features are in grid format data, where the relation between features and any knowledge of network topology is absent. Moreover, the traditional and common models, such as neural networks (NN), are not applicable if the input variables are in the graph format structure. Therefore, this paper examines the security analysis in the graph neural network (GNN) framework such that the GNN model incorporates the network connection and node's neighbors' influence for the assessment. Here the input features are separated graphs representing different network conditions in electrical and structural statuses. Topological characteristics defined by network centrality measures are added in the feature vector representing the structural properties of the network. The proposed model is simulated in the IEEE 118-Bus system for the voltage static security assessment (SSA). The performance indices validate the efficiency of the GNN-based model compared to the traditional NN model denoting that the information enclosed in graph data boosts the classifier performance since the GNN model benefits the neighbors' features. Moreover, outperforming of GNN-based model is determined when robustness and sensitivity analyzes are carried out. The proposed method is not limited to a specific task and can be extended for other security assessments with different critical variables, such as dynamic analysis and frequency criteria, respectively.

eess.SY↗

arXiv2022

Exploring Physical-Based Constraints in Short-Term Load Forecasting: A Defense Mechanism Against Cyberattack

Short-term load forecasting is an essential task that supports utilities to schedule generating sufficient power for balancing supply and demand, and can become an attractive target for cyber attacks. It has been shown that the power system state estimation is vulnerable to false data injection attacks. Similarly, false data injection on input variables can result in large forecast errors. The load forecasting system should have a protective mechanism to mitigate such attacks. One approach is to model physical system constraints that would identify anomalies. This study investigates possible constraints associated with a load forecasting application. Looking at regional forecasted loads, we analyze the relation between each zone through similarity measures used in time series in order to identify constraints. Comprehensive results for historical ERCOT load data indicate variation in the measures recognizing the existence of malicious action. Still, these static measures can not be considered an efficient index across different scenarios.

eess.SY↗

arXiv2021

Dynamic Multi-level Privilege Control in Behavior-based Implicit Authentication Systems Leveraging Mobile Devices

Implicit authentication (IA) is gaining popularity over recent years due to its use of user behavior as the main input, relieving users from explicit actions such as remembering and entering passwords. However, such convenience comes with a cost of authentication accuracy and delay which we propose to improve in this paper. Authentication accuracy deteriorates as users' behaviors change as a result of mood, age, a change of routine, etc. Current authentication systems handle failed authentication attempts by locking the users out of their mobile devices. It is unsuitable for IA whose accuracy deterioration induces a high false reject rate, rendering the IA system unusable. Furthermore, existing IA systems leverage computationally expensive machine learning, which can introduce a large authentication delay. It is challenging to improve the authentication accuracy of these systems without sacrificing authentication delay. In this paper, we propose a multi-level privilege control (MPC) scheme that dynamically adjusts users' access privilege based on their behavior change. MPC increases the system's confidence in users' legitimacy even when their behaviors deviate from historical data, thus improving authentication accuracy. It is a lightweight feature added to the existing IA schemes that helps avoid frequent and expensive retraining of machine learning models, thus improving authentication delay. We demonstrate that MPC increases authentication accuracy by 18.63\% and reduces authentication delay by 7.02 minutes on average, using a public dataset that contains comprehensive user behavior data.

cs.CR↗

arXiv2020

ConAML: Constrained Adversarial Machine Learning for Cyber-Physical Systems

Recent research demonstrated that the superficially well-trained machine learning (ML) models are highly vulnerable to adversarial examples. As ML techniques are becoming a popular solution for cyber-physical systems (CPSs) applications in research literatures, the security of these applications is of concern. However, current studies on adversarial machine learning (AML) mainly focus on pure cyberspace domains. The risks the adversarial examples can bring to the CPS applications have not been well investigated. In particular, due to the distributed property of data sources and the inherent physical constraints imposed by CPSs, the widely-used threat models and the state-of-the-art AML algorithms in previous cyberspace research become infeasible. We study the potential vulnerabilities of ML applied in CPSs by proposing Constrained Adversarial Machine Learning (ConAML), which generates adversarial examples that satisfy the intrinsic constraints of the physical systems. We first summarize the difference between AML in CPSs and AML in existing cyberspace systems and propose a general threat model for ConAML. We then design a best-effort search algorithm to iteratively generate adversarial examples with linear physical constraints. We evaluate our algorithms with simulations of two typical CPSs, the power grids and the water treatment system. The results show that our ConAML algorithms can effectively generate adversarial examples which significantly decrease the performance of the ML models even under practical constraints.

cs.CR↗

arXiv2020

Exploiting Vulnerabilities of Deep Learning-based Energy Theft Detection in AMI through Adversarial Attacks

Effective detection of energy theft can prevent revenue losses of utility companies and is also important for smart grid security. In recent years, enabled by the massive fine-grained smart meter data, deep learning (DL) approaches are becoming popular in the literature to detect energy theft in the advanced metering infrastructure (AMI). However, as neural networks are shown to be vulnerable to adversarial examples, the security of the DL models is of concern. In this work, we study the vulnerabilities of DL-based energy theft detection through adversarial attacks, including single-step attacks and iterative attacks. From the attacker's point of view, we design the \textit{SearchFromFree} framework that consists of 1) a randomly adversarial measurement initialization approach to maximize the stolen profit and 2) a step-size searching scheme to increase the performance of black-box iterative attacks. The evaluation based on three types of neural networks shows that the adversarial attacker can report extremely low consumption measurements to the utility without being detected by the DL models. We finally discuss the potential defense mechanisms against adversarial attacks in energy theft detection.

cs.CR↗

arXiv2020

SearchFromFree: Adversarial Measurements for Machine Learning-based Energy Theft Detection

Energy theft causes large economic losses to utility companies around the world. In recent years, energy theft detection approaches based on machine learning (ML) techniques, especially neural networks, become popular in the research literature and achieve state-of-the-art detection performance. However, in this work, we demonstrate that the well-perform ML models for energy theft detection are highly vulnerable to adversarial attacks. In particular, we design an adversarial measurement generation algorithm that enables the attacker to report extremely low power consumption measurements to the utilities while bypassing the ML energy theft detection. We evaluate our approach with three kinds of neural networks based on a real-world smart meter dataset. The evaluation result demonstrates that our approach can significantly decrease the ML models' detection accuracy, even for black-box attackers.

eess.SP↗

arXiv2018

A Practical Searchable Symmetric Encryption Scheme for Smart Grid Data

Outsourcing data storage to the remote cloud can be an economical solution to enhance data management in the smart grid ecosystem. To protect the privacy of data, the utility company may choose to encrypt the data before uploading them to the cloud. However, while encryption provides confidentiality to data, it also sacrifices the data owners' ability to query a special segment in their data. Searchable symmetric encryption is a technology that enables users to store documents in ciphertext form while keeping the functionality to search keywords in the documents. However, most state-of-the-art SSE algorithms are only focusing on general document storage, which may become unsuitable for smart grid applications. In this paper, we propose a simple, practical SSE scheme that aims to protect the privacy of data generated in the smart grid. Our scheme achieves high space complexity with small information disclosure that was acceptable for practical smart grid application. We also implement a prototype over the statistical data of advanced meter infrastructure to show the effectiveness of our approach.

cs.CR↗