Junggab Son

An Huang, Junggab Son, Zuobin Xiong

Diffusion models have become the foundation of modern generative systems, with most research focusing primarily on improving generation efficiency and output quality. The timestep embedding component is a crucial part of the diffusion pipeline, which provides a temporal conditioning signal to the denoising network, enabling it to adapt its predictions across different noise levels throughout the process. Despite their potential to contain substantial information, timestep embeddings remain underexplored in current research, especially for security risks and reliable provenance. To fill this gap, we introduce Shadow Timestep Embedding (STE), a novel mechanism that investigates the underutilized temporal space for malicious information injection into diffusion models. In particular, when zooming in on the timestep embedding space, we find that different timesteps exhibit distinct representational capabilities that can encode side-channel information. Moreover, such encoded information can be utilized for attack and defense purposes through the scheduler interface. We present a theoretical analysis of timestep embeddings as position-encoding mappings and derive a mutual coherence evaluation that explains the separability of disjoint timestep intervals. Our findings reveal the diffusion model's timestep as a powerful side channel for carrying dedicated information, motivating new directions for adversarial generative modeling by understanding the temporal dimension.

Suprim Nakarmi, Junggab Son, Yue Zhao et al.

Graph Neural Networks (GNNs) have been intensively studied for their expressive representation and learning performance on graph-structured data, enabling effective modeling of complex relational dependencies among nodes and edges in various domains. However, the standalone GNNs can unleash threat surfaces and privacy implications, as some sensitive graph-structured data is collected and processed in a centralized setting. To solve this issue, Federated Graph Neural Networks (FedGNNs) are proposed to facilitate collaborative learning over decentralized local graph data, aiming to preserve user privacy. Yet, emerging research indicates that even in these settings, shared model updates, particularly gradients, can unintentionally leak sensitive information of local users. Numerous privacy inference attacks have been explored in traditional federated learning and extended to graph settings, but the problem of label distribution inference in FedGNNs remains largely underexplored. In this work, we introduce Fed-Listing (Federated Label Distribution Inference in GNNs), a novel gradient-based attack designed to infer the private label statistics of target clients in FedGNNs without access to raw data or node features. Fed-Listing only leverages the final-layer gradients exchanged during training to uncover statistical patterns that reveal class proportions in a stealthy manner. An auxiliary shadow dataset is used to generate diverse label partitioning strategies, simulating various client distributions, on which the attack model is obtained. Extensive experiments on four benchmark datasets and three GNN architectures show that Fed-Listing significantly outperforms existing baselines, including random guessing and Decaf, even under challenging non-i.i.d. scenarios. Moreover, applying defense mechanisms can barely reduce our attack performance, unless the model's utility is severely degraded.

Tejaswini Mallavarapu, Luke Cranfill, Junggab Son et al.

As online retail services proliferate and are pervasive in modern lives, applications for classifying fashion apparel features from image data are becoming more indispensable. Online retailers, from leading companies to start-ups, can leverage such applications in order to increase profit margin and enhance the consumer experience. Many notable schemes have been proposed to classify fashion items, however, the majority of which focused upon classifying basic-level categories, such as T-shirts, pants, skirts, shoes, bags, and so forth. In contrast to most prior efforts, this paper aims to enable an in-depth classification of fashion item attributes within the same category. Beginning with a single dress, we seek to classify the type of dress hem, the hem length, and the sleeve length. The proposed scheme is comprised of three major stages: (a) localization of a target item from an input image using semantic segmentation, (b) detection of human key points (e.g., point of shoulder) using a pre-trained CNN and a bounding box, and (c) three phases to classify the attributes using a combination of algorithmic approaches and deep neural networks. The experimental results demonstrate that the proposed scheme is highly effective, with all categories having average precision of above 93.02%, and outperforms existing Convolutional Neural Networks (CNNs)-based schemes.

Rasheed Hussain, Donghyun Kim, Michele Nogueira et al.

Recently an online electric vehicle (OLEV) concept has been introduced, where vehicles are propelled through the wirelessly transmitted electrical power from the infrastructure installed under the road while moving. The absence of secure-and-fair billing is one main hurdle to widely adopt this promising technology. This paper introduces a secure and privacy-aware fair billing framework for OLEV on the move through the charging plates installed under the road. We first propose two extreme lightweight mutual authentication mechanisms, a direct authentication and a hash chain-based authentication between vehicles and the charging plates that can be used for different vehicular speeds on the road. Second we propose a secure and privacy-aware wireless power transfer on move for the vehicles with bidirectional auditability guarantee by leveraging game-theoretic approach. Each charging plate transfers a fixed amount of energy to the vehicle and bills the vehicle in a privacy-aware way accordingly. Our protocol guarantees secure, privacy-aware, and fair billing mechanism for the OLEVs while receiving electric power from the road. Moreover our proposed framework can play a vital role in eliminating the security and privacy challenges in the deployment of power transfer technology to the OLEVs.