Yuan Hong

Shangyu Xie, Han Wang, Shengbin Wang et al.

Smart grid has integrated an increasing number of distributed energy resources to improve the efficiency and flexibility of power generation and consumption as well as the resilience of the power grid. The energy consumers on the power grid (e.g., households) equipped with the distributed energy resources can be considered as "microgrids" that both generate and consume electricity. In this paper, we study the energy community discovery problems which identify multiple kinds of energy communities for the microgrids to facilitate energy management (e.g., power supply adjustment, load balancing, energy sharing) on the grid, such as homogeneous energy communities (HECs), mixed energy communities (MECs), and self-sufficient energy communities (SECs). Specifically, we present efficient algorithms to discover such communities of microgrids by taking into account not only their geo-locations but also their net energy over any period. Finally, we experimentally validate the performance of the algorithms using both synthetic and real datasets.

Shuya Feng, Meisam Mohammady, Hanbin Hong et al.

Differentially private federated learning (DP-FL) is a promising technique for collaborative model training while ensuring provable privacy for clients. However, optimizing the tradeoff between privacy and accuracy remains a critical challenge. To our best knowledge, we propose the first DP-FL framework (namely UDP-FL), which universally harmonizes any randomization mechanism (e.g., an optimal one) with the Gaussian Moments Accountant (viz. DP-SGD) to significantly boost accuracy and convergence. Specifically, UDP-FL demonstrates enhanced model performance by mitigating the reliance on Gaussian noise. The key mediator variable in this transformation is the Rényi Differential Privacy notion, which is carefully used to harmonize privacy budgets. We also propose an innovative method to theoretically analyze the convergence for DP-FL (including our UDP-FL ) based on mode connectivity analysis. Moreover, we evaluate our UDP-FL through extensive experiments benchmarked against state-of-the-art (SOTA) methods, demonstrating superior performance on both privacy guarantees and model performance. Notably, UDP-FL exhibits substantial resilience against different inference attacks, indicating a significant advance in safeguarding sensitive data in federated learning environments.

Zhenghao Zhao, Haoxuan Wang, Kai Wang et al.

Dataset distillation aims to synthesize compact yet informative datasets that allow models trained on them to achieve performance comparable to training on the full dataset. While this approach has shown promising results for image data, extending dataset distillation methods to video data has proven challenging and often leads to suboptimal performance. In this work, we first identify the core challenge in video set distillation as the substantial increase in learnable parameters introduced by the temporal dimension of video, which complicates optimization and hinders convergence. To address this issue, we observe that a single frame is often sufficient to capture the discriminative semantics of a video. Leveraging this insight, we propose Single-Frame Video set Distillation (SFVD), a framework that distills videos into highly informative frames for each class. Using differentiable interpolation, these frames are transformed into video sequences and matched with the original dataset, while updates are restricted to the frames themselves for improved optimization efficiency. To further incorporate temporal information, the distilled frames are combined with sampled real videos from real videos during the matching process through a channel reshaping layer. Extensive experiments on multiple benchmarks demonstrate that SFVD substantially outperforms prior methods, achieving improvements of up to 5.3% on MiniUCF, thereby offering a more effective solution.

Qin Yang, Nicholas Stout, Meisam Mohammady et al.

Differentially Private Stochastic Gradient Descent (DP-SGD) is a standard method for enforcing privacy in deep learning, typically using the Gaussian mechanism to perturb gradient updates. However, conventional mechanisms such as Gaussian and Laplacian noise are parameterized only by variance or scale. This single degree of freedom ties the magnitude of noise directly to both privacy loss and utility degradation, preventing independent control of these two factors. The problem becomes more pronounced when the number of composition rounds T and batch size B vary across tasks, as these variations induce task-dependent shifts in the privacy-utility trade-off, where small changes in noise parameters can disproportionately affect model accuracy. To address this limitation, we introduce PLRV-O, a framework that defines a broad search space of parameterized DP-SGD noise distributions, where privacy loss moments are tightly characterized yet can be optimized more independently with respect to utility loss. This formulation enables systematic adaptation of noise to task-specific requirements, including (i) model size, (ii) training duration, (iii) batch sampling strategies, and (iv) clipping thresholds under both training and fine-tuning settings. Empirical results demonstrate that PLRV-O substantially improves utility under strict privacy constraints. On CIFAR-10, a fine-tuned ViT achieves 94.03% accuracy at epsilon approximately 0.5, compared to 83.93% with Gaussian noise. On SST-2, RoBERTa-large reaches 92.20% accuracy at epsilon approximately 0.2, versus 50.25% with Gaussian.

Shenao Yan, Shen Wang, Yue Duan et al.

Large Language Models (LLMs) have transformed code completion tasks, providing context-based suggestions to boost developer productivity in software engineering. As users often fine-tune these models for specific applications, poisoning and backdoor attacks can covertly alter the model outputs. To address this critical security challenge, we introduce CodeBreaker, a pioneering LLM-assisted backdoor attack framework on code completion models. Unlike recent attacks that embed malicious payloads in detectable or irrelevant sections of the code (e.g., comments), CodeBreaker leverages LLMs (e.g., GPT-4) for sophisticated payload transformation (without affecting functionalities), ensuring that both the poisoned data for fine-tuning and generated code can evade strong vulnerability detection. CodeBreaker stands out with its comprehensive coverage of vulnerabilities, making it the first to provide such an extensive set for evaluation. Our extensive experimental evaluations and user studies underline the strong attack performance of CodeBreaker across various settings, validating its superiority over existing approaches. By integrating malicious payloads directly into the source code with minimal transformation, CodeBreaker challenges current security measures, underscoring the critical need for more robust defenses for code completion.

Shangyu Xie, Bingyu Liu, Yuan Hong

Deep learning as a service (DLaaS) has been intensively studied to facilitate the wider deployment of the emerging deep learning applications. However, DLaaS may compromise the privacy of both clients and cloud servers. Although some privacy preserving deep neural network (DNN) based inference techniques have been proposed by composing cryptographic primitives, the challenges on computational efficiency have not been well-addressed due to the complexity of DNN models and expensive cryptographic primitives. In this paper, we propose a novel privacy preserving cloud-based DNN inference framework (namely, "PROUD"), which greatly improves the computational efficiency. Finally, we conduct extensive experiments on two commonly-used datasets to validate both effectiveness and efficiency for the PROUD, which also outperforms the state-of-the-art techniques.

Shangyu Xie, Han Wang, Yuan Hong et al.

The smart grid incentivizes distributed agents with local generation (e.g., smart homes, and microgrids) to establish multi-agent systems for enhanced reliability and energy consumption efficiency. Distributed energy trading has emerged as one of the most important multi-agent systems on the power grid by enabling agents to sell their excessive local energy to each other or back to the grid. However, it requests all the agents to disclose their sensitive data (e.g., each agent's fine-grained local generation and demand load). In this paper, to the best of our knowledge, we propose the first privacy preserving distributed energy trading framework, Private Energy Market (PEM), in which all the agents privately compute an optimal price for their trading (ensured by a Nash Equilibrium), and allocate pairwise energy trading amounts without disclosing sensitive data (via novel cryptographic protocols). Specifically, we model the trading problem as a non-cooperative Stackelberg game for all the agents (i.e., buyers and sellers) to determine the optimal price, and then derive the pairwise trading amounts. Our PEM framework can privately perform all the computations among all the agents without a trusted third party. We prove the privacy, individual rationality, and incentive compatibility for the PEM framework. Finally, we conduct experiments on real datasets to validate the effectiveness and efficiency of the PEM.

Han Wang, Shangyu Xie, Yuan Hong

Massive amounts of video data are ubiquitously generated in personal devices and dedicated video recording facilities. Analyzing such data would be extremely beneficial in real world (e.g., urban traffic analysis, pedestrian behavior analysis, video surveillance). However, videos contain considerable sensitive information, such as human faces, identities and activities. Most of the existing video sanitization techniques simply obfuscate the video by detecting and blurring the region of interests (e.g., faces, vehicle plates, locations and timestamps) without quantifying and bounding the privacy leakage in the sanitization. In this paper, to the best of our knowledge, we propose the first differentially private video analytics platform (VideoDP) which flexibly supports different video analyses with rigorous privacy guarantee. Different from traditional noise-injection based differentially private mechanisms, given the input video, VideoDP randomly generates a utility-driven private video in which adding or removing any sensitive visual element (e.g., human, object) does not significantly affect the output video. Then, different video analyses requested by untrusted video analysts can be flexibly performed over the utility-driven video while ensuring differential privacy. Finally, we conduct experiments on real videos, and the experimental results demonstrate that our VideoDP effectively functions video analytics with good utility.

Chen Change Loy, Dahua Lin, Wanli Ouyang et al.

This paper presents a review of the 2018 WIDER Challenge on Face and Pedestrian. The challenge focuses on the problem of precise localization of human faces and bodies, and accurate association of identities. It comprises of three tracks: (i) WIDER Face which aims at soliciting new approaches to advance the state-of-the-art in face detection, (ii) WIDER Pedestrian which aims to find effective and efficient approaches to address the problem of pedestrian detection in unconstrained environments, and (iii) WIDER Person Search which presents an exciting challenge of searching persons across 192 movies. In total, 73 teams made valid submissions to the challenge tracks. We summarize the winning solutions for all three tracks. and present discussions on open problems and potential research directions in these topics.

Meisam Mohammady, Lingyu Wang, Yuan Hong et al.

As network security monitoring grows more sophisticated, there is an increasing need for outsourcing such tasks to third-party analysts. However, organizations are usually reluctant to share their network traces due to privacy concerns over sensitive information, e.g., network and system configuration, which may potentially be exploited for attacks. In cases where data owners are convinced to share their network traces, the data are typically subjected to certain anonymization techniques, e.g., CryptoPAn, which replaces real IP addresses with prefix-preserving pseudonyms. However, most such techniques either are vulnerable to adversaries with prior knowledge about some network flows in the traces, or require heavy data sanitization or perturbation, both of which may result in a significant loss of data utility. In this paper, we aim to preserve both privacy and utility through shifting the trade-off from between privacy and utility to between privacy and computational cost. The key idea is for the analysts to generate and analyze multiple anonymized views of the original network traces; those views are designed to be sufficiently indistinguishable even to adversaries armed with prior knowledge, which preserves the privacy, whereas one of the views will yield true analysis results privately retrieved by the data owner, which preserves the utility. We present the general approach and instantiate it based on CryptoPAn. We formally analyze the privacy of our solution and experimentally evaluate it using real network traces provided by a major ISP. The results show that our approach can significantly reduce the level of information leakage (e.g., less than 1\% of the information leaked by CryptoPAn) with comparable utility.

Yuan Hong, Jaideep Vaidya, Haibing Lu

Combinatorial optimization is a fundamental problem found in many fields. In many real life situations, the constraints and the objective function forming the optimization problem are naturally distributed amongst different sites in some fashion. A typical approach for solving such problem is to collect all of this information together and centrally solve the problem. However, this requires all parties to completely share their information, which may lead to serious privacy issues. Thus, it is desirable to propose a privacy preserving technique that can securely solve specific combinatorial optimization problems. A further complicating factor is that combinatorial optimization problems are typically NP-hard, requiring approximation algorithms or heuristics to provide a practical solution. In this paper, we focus on a very well-known hard problem -- the distributed graph coloring problem, which has been utilized to model many real world problems in scheduling and resource allocation. We propose efficient protocols to securely solve such fundamental problem. We analyze the security of our approach and experimentally demonstrate the effectiveness of our approach.

Yuan Hong, Han Wang, Shangyu Xie et al.

Energy has been increasingly generated or collected by different entities on the power grid (e.g., universities, hospitals and householdes) via solar panels, wind turbines or local generators in the past decade. With local energy, such electricity consumers can be considered as "microgrids" which can simulataneously generate and consume energy. Some microgrids may have excessive energy that can be shared to other power consumers on the grid. To this end, all the entities have to share their local private information (e.g., their local demand, local supply and power quality data) to each other or a third-party to find and implement the optimal energy sharing solution. However, such process is constrained by privacy concerns raised by the microgrids. In this paper, we propose a privacy preserving scheme for all the microgrids which can securely implement their energy sharing against both semi-honest and colluding adversaries. The proposed approach includes two secure communication protocols that can ensure quantified privacy leakage and handle collusions.

Yuan Hong, Jaideep Vaidya, Nicholas Rizzo et al.

With the rapid increase in computing, storage and networking resources, data is not only collected and stored, but also analyzed. This creates a serious privacy problem which often inhibits the use of this data. In this chapter, we investigate and resolve the privacy issues in a fundamental optimization problem -- linear programming (LP) which is formulated by data collected from different parties. We first consider the case where the objective function and constraints of the linear programming problem are not partitioned between two parties where one party privately holds the objective function while the other party privately holds the constraints. Second, we present a privacy preserving technique for the case that objective function and constraints are arbitrarily partitioned between two parties where each party privately holds a share of objective function and constraints. Finally, we extend the technique for securely solving two-party arbitrarily partitioned linear programming problems to a multi-party scenario. In summary, we propose a set of efficient and secure transformation based techniques that create significant value-added benefits of being independent of the specific algorithms used for solving the linear programming problem.

Nicholas Rizzo, Ethan Sprissler, Yuan Hong et al.

In order to better manage the premiums and encourage safe driving, many commercial insurance companies (e.g., Geico, Progressive) are providing options for their customers to install sensors on their vehicles which collect individual vehicle's traveling data. The driver's insurance is linked to his/her driving behavior. At the other end, through analyzing the historical traveling data from a large number of vehicles, the insurance company could build a classifier to predict a new driver's driving style: aggressive or defensive. However, collection of such vehicle traveling data explicitly breaches the drivers' personal privacy. To tackle such privacy concerns, this paper presents a privacy-preserving driving style recognition technique to securely predict aggressive and defensive drivers for the insurance company without compromising the privacy of all the participating parties. The insurance company cannot learn any private information from the vehicles, and vice-versa. Finally, the effectiveness and efficiency of the privacy-preserving driving style recognition technique are validated with experimental results.