arXiv subjects

Zhenpeng Shi

Publications and source records attributed to Zhenpeng Shi.

4 recordsLinked to original sources

arXiv2026

Revealing Safety-Critical Scenarios for UTM via Transformer

Unmanned Traffic Management (UTM) systems are cloud-based platforms designed to manage and coordinate multiple aerial vehicles remotely. UTM systems are safety-critical which cannot tolerate failures like crash or collision. To reveal latent vulnerabilities, there are neither optimal failure-exposing demonstrations nor clear reward signals. Additionally, UTM's self-healing capability introduces the ``long-tail effect'' of critical failures. We propose framing UTM vulnerability discovery as a sequence modeling problem amenable to transformer-based RL architectures. Our approach leverages attention mechanisms to directly model the relationship among system states, and predict optimal actions. Our framework introduces a Policy Model that generates targeted test scenarios and an Action Sampler that enforces domain constraints. We use a risk-based reward function to guide exploration. Through extensive evaluation on a 700-hour simulation study, we demonstrate an 8$\times$ improvement in vulnerability discovery efficiency compared to expert-guided testing. It also discovers critical edge cases that traditional methods have missed.

cs.AI↗

arXiv2023

AQUILA: Communication Efficient Federated Learning with Adaptive Quantization in Device Selection Strategy

The widespread adoption of Federated Learning (FL), a privacy-preserving distributed learning methodology, has been impeded by the challenge of high communication overheads, typically arising from the transmission of large-scale models. Existing adaptive quantization methods, designed to mitigate these overheads, operate under the impractical assumption of uniform device participation in every training round. Additionally, these methods are limited in their adaptability due to the necessity of manual quantization level selection and often overlook biases inherent in local devices' data, thereby affecting the robustness of the global model. In response, this paper introduces AQUILA (adaptive quantization in device selection strategy), a novel adaptive framework devised to effectively handle these issues, enhancing the efficiency and robustness of FL. AQUILA integrates a sophisticated device selection method that prioritizes the quality and usefulness of device updates. Utilizing the exact global model stored by devices, it enables a more precise device selection criterion, reduces model deviation, and limits the need for hyperparameter adjustments. Furthermore, AQUILA presents an innovative quantization criterion, optimized to improve communication efficiency while assuring model convergence. Our experiments demonstrate that AQUILA significantly decreases communication costs compared to existing methods, while maintaining comparable model performance across diverse non-homogeneous FL settings, such as Non-IID data and heterogeneous model architectures.

cs.LG↗

arXiv2023

Inclusive Data Representation in Federated Learning: A Novel Approach Integrating Textual and Visual Prompt

Federated Learning (FL) is often impeded by communication overhead issues. Prompt tuning, as a potential solution, has been introduced to only adjust a few trainable parameters rather than the whole model. However, current single-modality prompt tuning approaches fail to comprehensively portray local clients' data. To overcome this limitation, we present Twin Prompt Federated learning (TPFL), a pioneering solution that integrates both visual and textual modalities, ensuring a more holistic representation of local clients' data characteristics. Furthermore, in order to tackle the data heterogeneity issues, we introduce the Augmented TPFL (ATPFL) employing the contrastive learning to TPFL, which not only enhances the global knowledge acquisition of client models but also fosters the development of robust, compact models. The effectiveness of TPFL and ATPFL is substantiated by our extensive evaluations, consistently showing superior performance compared to all baselines.

cs.LG↗

arXiv2023

Uncovering CWE-CVE-CPE Relations with Threat Knowledge Graphs

Security assessment relies on public information about products, vulnerabilities, and weaknesses. So far, databases in these categories have rarely been analyzed in combination. Yet, doing so could help predict unreported vulnerabilities and identify common threat patterns. In this paper, we propose a methodology for producing and optimizing a knowledge graph that aggregates knowledge from common threat databases (CVE, CWE, and CPE). We apply the threat knowledge graph to predict associations between threat databases, specifically between products, vulnerabilities, and weaknesses. We evaluate the prediction performance both in closed world with associations from the knowledge graph, and in open world with associations revealed afterward. Using rank-based metrics (i.e., Mean Rank, Mean Reciprocal Rank, and Hits@N scores), we demonstrate the ability of the threat knowledge graph to uncover many associations that are currently unknown but will be revealed in the future, which remains useful over different time periods. We propose approaches to optimize the knowledge graph, and show that they indeed help in further uncovering associations.

cs.CR↗