arXiv subjects

Zhiliang Wang

Publications and source records attributed to Zhiliang Wang.

14 recordsLinked to original sources

arXiv2026

TORCH: Characterizing Invalid Route Filtering via Tunnelled Observation

To mitigate BGP prefix hijacking, the Resource Public Key Infrastructure (RPKI) provides prefix origin authentication via Route Origin Validation (ROV). Despite extensive measurement efforts in IPv4, the protective impact of ROV in IPv6 has yet to be systematically assessed. Existing approaches suffer from limited observability into invalid route propagation: they often rely on a small set of controlled prefixes or cannot fully profile the filtering of in-the-wild RPKI-invalid routes, which undermines the accuracy of assessment. Furthermore, the inherent opacity of the IPv6 data plane exacerbates the difficulty of performing scalable and reliable active measurements. In this paper, we present TORCH, a novel framework for measuring invalid route filtering in IPv6. It repurposes open 6in4 tunnel endpoints as widely distributed vantage points for global measurement. At its core, we develop a cross-plane inference technique that determines reachability without requiring responsive targets. This method allows us to characterize whether and how traffic is steered to invalid origins across diverse routing scenarios, leading to an in-depth evaluation of the real-world impact of ROV. Our measurements reveal that about 27\% of ASes have achieved nearly full ROV protection. However, several permissive Tier-1 ASes still transit traffic towards invalid origins, maintaining a substantial attack surface. Through a prefix-centric analysis, we provide the first empirical evidence that the collateral damage of same-length prefix filtering can affect a significant fraction of the global Internet. Our findings pinpoint fundamental vulnerabilities in ROV deployment and underscore the urgent necessity for network operators to accelerate RPKI adoption. We make our datasets publicly available.

cs.NI↗

arXiv2025

Unsupervised Domain Adaptation with Dynamic Clustering and Contrastive Refinement for Gait Recognition

Gait recognition is an emerging identification technology that distinguishes individuals at long distances by analyzing individual walking patterns. Traditional techniques rely heavily on large-scale labeled datasets, which incurs high costs and significant labeling challenges. Recently, researchers have explored unsupervised gait recognition with clustering-based unsupervised domain adaptation methods and achieved notable success. However, these methods directly use pseudo-label generated by clustering and neglect pseudolabel noise caused by domain differences, which affects the effect of the model training process. To mitigate these issues, we proposed a novel model called GaitDCCR, which aims to reduce the influence of noisy pseudo labels on clustering and model training. Our approach can be divided into two main stages: clustering and training stage. In the clustering stage, we propose Dynamic Cluster Parameters (DCP) and Dynamic Weight Centroids (DWC) to improve the efficiency of clustering and obtain reliable cluster centroids. In the training stage, we employ the classical teacher-student structure and propose Confidence-based Pseudo-label Refinement (CPR) and Contrastive Teacher Module (CTM) to encourage noisy samples to converge towards clusters containing their true identities. Extensive experiments on public gait datasets have demonstrated that our simple and effective method significantly enhances the performance of unsupervised gait recognition, laying the foundation for its application in the real-world. We will release the code at https://github.com/YanSun-github/GaitDCCR upon acceptance.

cs.CV↗

arXiv2024

FG-SAT: Efficient Flow Graph for Encrypted Traffic Classification under Environment Shifts

Encrypted traffic classification plays a critical role in network security and management. Currently, mining deep patterns from side-channel contents and plaintext fields through neural networks is a major solution. However, existing methods have two major limitations: (1) They fail to recognize the critical link between transport layer mechanisms and applications, missing the opportunity to learn internal structure features for accurate traffic classification. (2) They assume network traffic in an unrealistically stable and singular environment, making it difficult to effectively classify real-world traffic under environment shifts. In this paper, we propose FG-SAT, the first end-to-end method for encrypted traffic analysis under environment shifts. We propose a key abstraction, the Flow Graph, to represent flow internal relationship structures and rich node attributes, which enables robust and generalized representation. Additionally, to address the problem of inconsistent data distribution under environment shifts, we introduce a novel feature selection algorithm based on Jensen-Shannon divergence (JSD) to select robust node attributes. Finally, we design a classifier, GraphSAT, which integrates GraphSAGE and GAT to deeply learn Flow Graph features, enabling accurate encrypted traffic identification. FG-SAT exhibits both efficient and robust classification performance under environment shifts and outperforms state-of-the-art methods in encrypted attack detection and application classification.

cs.CR↗

arXiv2024

Centralized Network Utility Maximization with Accelerated Gradient Method

Network utility maximization (NUM) is a well-studied problem for network traffic management and resource allocation. Because of the inherent decentralization and complexity of networks, most researches develop decentralized NUM algorithms. In recent years, the Software Defined Networking (SDN) architecture has been widely used, especially in cloud networks and inter-datacenter networks managed by large enterprises, promoting the design of centralized NUM algorithms. To cope with the large and increasing number of flows in such SDN networks, existing researches about centralized NUM focus on the scalability of the algorithm with respect to the number of flows, however the efficiency is ignored. In this paper, we focus on the SDN scenario, and derive a centralized, efficient and scalable algorithm for the NUM problem. By the designing of a smooth utility function and a smooth penalty function, we formulate the NUM problem with a smooth objective function, which enables the use of Nesterov's accelerated gradient method. We prove that the proposed method has $O(d/t^2)$ convergence rate, which is the fastest with respect to the number of iterations $t$, and our method is scalable with respect to the number of flows $d$ in the network. Experiments show that our method obtains accurate solutions with less iterations, and achieves close-to-optimal network utility.

cs.NI↗

arXiv2024

Explainable and Transferable Adversarial Attack for ML-Based Network Intrusion Detectors

espite being widely used in network intrusion detection systems (NIDSs), machine learning (ML) has proven to be highly vulnerable to adversarial attacks. White-box and black-box adversarial attacks of NIDS have been explored in several studies. However, white-box attacks unrealistically assume that the attackers have full knowledge of the target NIDSs. Meanwhile, existing black-box attacks can not achieve high attack success rate due to the weak adversarial transferability between models (e.g., neural networks and tree models). Additionally, neither of them explains why adversarial examples exist and why they can transfer across models. To address these challenges, this paper introduces ETA, an Explainable Transfer-based Black-Box Adversarial Attack framework. ETA aims to achieve two primary objectives: 1) create transferable adversarial examples applicable to various ML models and 2) provide insights into the existence of adversarial examples and their transferability within NIDSs. Specifically, we first provide a general transfer-based adversarial attack method applicable across the entire ML space. Following that, we exploit a unique insight based on cooperative game theory and perturbation interpretations to explain adversarial examples and adversarial transferability. On this basis, we propose an Important-Sensitive Feature Selection (ISFS) method to guide the search for adversarial examples, achieving stronger transferability and ensuring traffic-space constraints.

cs.CR↗

arXiv2023

Consistent temporal behaviors over a non-Newtonian/Newtonian two-phase flow

The temporal behaviors of non-Newtonian/Newtonian two-phase flows are closely tied to flow pattern formation mechanisms, influenced significantly by the non-Newtonian index, and exhibiting nonlinear rheological characteristics. The rheological model parameters are model-dependent, resulting in poor predictability of their spatio-temporal characteristics. This limitation hinders the development of a unified analytical approach and consistent results, confining researches to case-by-case studies. In this study, sets of digital microfluidics experiments, along with continuous-discrete phase-interchanging schemes, yielded 72 datasets under various non-Newtonian fluid solution configurations, micro-channel structures, and multiple Carreau-related models. Among these datasets, we identified consistent temporal behaviors featuring non-Newtonian flow patterns in digital microfluidics. In the context of significant model dependency and widespread uncertainty in model parameters for non-Newtonian fluid characterization, this study demonstrates that the consistent representation of the non-Newtonian behavior exit, and may be essentially independent of specific data or models. Which finding holds positive implications for understanding the flow behavior and morphology of non-Newtonian fluids.

physics.flu-dyn↗

arXiv2023

Your Router is My Prober: Measuring IPv6 Networks via ICMP Rate Limiting Side Channels

Active Internet measurements face challenges when some measurements require many remote vantage points. In this paper, we propose a novel technique for measuring remote IPv6 networks via side channels in ICMP rate limiting, a required function for IPv6 nodes to limit the rate at which ICMP error messages are generated. This technique, iVantage, can to some extent use 1.1M remote routers distributed in 9.5k autonomous systems and 182 countries as our "vantage points". We apply iVantage to two different, but both challenging measurement tasks: 1) measuring the deployment of inbound source address validation (ISAV) and 2) measuring reachability between arbitrary Internet nodes. We accomplish these two tasks from only one local vantage point without controlling the targets or relying on other services within the target networks. Our large-scale ISAV measurements cover ~50% of all IPv6 autonomous systems and find ~79% of them are vulnerable to spoofing, which is the most large-scale measurement study of IPv6 ISAV to date. Our method for reachability measurements achieves over 80% precision and recall in our evaluation. Finally, we perform an Internet-wide measurement of the ICMP rate limiting implementations, present a detailed discussion on ICMP rate limiting, particularly the potential security and privacy risks in the mechanism of ICMP rate limiting, and provide possible mitigation measures. We make our code available to the community.

cs.NI↗

arXiv2021

threaTrace: Detecting and Tracing Host-based Threats in Node Level Through Provenance Graph Learning

Host-based threats such as Program Attack, Malware Implantation, and Advanced Persistent Threats (APT), are commonly adopted by modern attackers. Recent studies propose leveraging the rich contextual information in data provenance to detect threats in a host. Data provenance is a directed acyclic graph constructed from system audit data. Nodes in a provenance graph represent system entities (e.g., $processes$ and $files$) and edges represent system calls in the direction of information flow. However, previous studies, which extract features of the whole provenance graph, are not sensitive to the small number of threat-related entities and thus result in low performance when hunting stealthy threats. We present threaTrace, an anomaly-based detector that detects host-based threats at system entity level without prior knowledge of attack patterns. We tailor GraphSAGE, an inductive graph neural network, to learn every benign entity's role in a provenance graph. threaTrace is a real-time system, which is scalable of monitoring a long-term running host and capable of detecting host-based intrusion in their early phase. We evaluate threaTrace on three public datasets. The results show that threaTrace outperforms three state-of-the-art host intrusion detection systems.

cs.CR↗

arXiv2021

DeepAID: Interpreting and Improving Deep Learning-based Anomaly Detection in Security Applications

Unsupervised Deep Learning (DL) techniques have been widely used in various security-related anomaly detection applications, owing to the great promise of being able to detect unforeseen threats and superior performance provided by Deep Neural Networks (DNN). However, the lack of interpretability creates key barriers to the adoption of DL models in practice. Unfortunately, existing interpretation approaches are proposed for supervised learning models and/or non-security domains, which are unadaptable for unsupervised DL models and fail to satisfy special requirements in security domains. In this paper, we propose DeepAID, a general framework aiming to (1) interpret DL-based anomaly detection systems in security domains, and (2) improve the practicality of these systems based on the interpretations. We first propose a novel interpretation method for unsupervised DNNs by formulating and solving well-designed optimization problems with special constraints for security domains. Then, we provide several applications based on our Interpreter as well as a model-based extension Distiller to improve security systems by solving domain-specific problems. We apply DeepAID over three types of security-related anomaly detection systems and extensively evaluate our Interpreter with representative prior works. Experimental results show that DeepAID can provide high-quality interpretations for unsupervised DL models while meeting the special requirements of security domains. We also provide several use cases to show that DeepAID can help security operators to understand model decisions, diagnose system mistakes, give feedback to models, and reduce false positives.

cs.CR↗

arXiv2021

Evaluating and Improving Adversarial Robustness of Machine Learning-Based Network Intrusion Detectors

Machine learning (ML), especially deep learning (DL) techniques have been increasingly used in anomaly-based network intrusion detection systems (NIDS). However, ML/DL has shown to be extremely vulnerable to adversarial attacks, especially in such security-sensitive systems. Many adversarial attacks have been proposed to evaluate the robustness of ML-based NIDSs. Unfortunately, existing attacks mostly focused on feature-space and/or white-box attacks, which make impractical assumptions in real-world scenarios, leaving the study on practical gray/black-box attacks largely unexplored. To bridge this gap, we conduct the first systematic study of the gray/black-box traffic-space adversarial attacks to evaluate the robustness of ML-based NIDSs. Our work outperforms previous ones in the following aspects: (i) practical-the proposed attack can automatically mutate original traffic with extremely limited knowledge and affordable overhead while preserving its functionality; (ii) generic-the proposed attack is effective for evaluating the robustness of various NIDSs using diverse ML/DL models and non-payload-based features; (iii) explainable-we propose an explanation method for the fragile robustness of ML-based NIDSs. Based on this, we also propose a defense scheme against adversarial attacks to improve system robustness. We extensively evaluate the robustness of various NIDSs using diverse feature sets and ML/DL models. Experimental results show our attack is effective (e.g., >97% evasion rate in half cases for Kitsune, a state-of-the-art NIDS) with affordable execution cost and the proposed defense method can effectively mitigate such attacks (evasion rate is reduced by >50% in most cases).

cs.CR↗

arXiv2019

Placement and Routing Optimization Problem for Service Function Chain: State of Art and Future Opportunities

Network Functions Virtualization (NFV) allows implantation of network functions to be independent of dedicated hardware devices. Any series of services can be represented by a service function chain which contains a set of virtualized network functions in a specified order. From the perspective of network performance optimization, the challenges of deploying service chain in network is twofold: 1) the location of placing virtualized network functions and resources allocation scheme; and 2) routing policy for traffic flow among different instances of network function. This article introduces service function chain related optimization problems, summarizes the optimization motivation and mainstream algorithm of virtualized network functions deployment and traffic routing. We hope it can help readers to learn about the current research progress and make further innovation in this field.

cs.NI↗

arXiv2018

PriMe: Per-Flow Network Measurement by Combining SRAM with DRAM

Network measurement is necessary to obtain an understanding of the network traffic and keep the network healthy. Flow-level measurement is widely used because it provides rich enough information while being resource efficient, in contrast to the traffic-level solutions like SNMP and packet-level solutions like tcpdump. Flow-level measurement requires to maintain a TFR for each active flow, and update the corresponding TFR when a packet arrives. In the scenario of high-speed networks, the processing time for each packet is only several or tens of nanoseconds, and there may be up to millions of concurrent active flows. Two requirements have to be met to be able to do flow-level measurement in this scenario, i.e., the memory size have to be large enough to maintain a TFR for each flow, and the access time of the memory have to be small enough to be able to update the TFR for each packet. Unfortunately, SRAM, which is fast enough, is expensive and there are limited amount available for the measurement tasks, while DRAM, which is large in capacity, is slow and cannot support the per-packet access. In this paper, we proposed a solution, PriMe, by combining SRAM with DRAM, overcoming the resource limitation by exporting TFRs to the DRAM when necessary, while enjoying the fast access of SRAM. We designed a peculiar algorithm to reduce the frequency of exporting TFRs to DRAM, as well as an algorithm to reduce the accesses of DRAM in aggregating the TFRs exported from SRAM.

cs.NI↗

arXiv2018

HashFlow For Better Flow Record Collection

Collecting flow records is a common practice of network operators and researchers for monitoring, diagnosing and understanding a network. Traditional tools like NetFlow face great challenges when both the speed and the complexity of the network traffic increase. To keep pace up, we propose HashFlow, a tool for more efficient and accurate collection and analysis of flow records. The central idea of HashFlow is to maintain accurate records for elephant flows, but summarized records for mice flows, by applying a novel collision resolution and record promotion strategy to hash tables. The performance bound can be analyzed with a probabilistic model, and with this strategy, HashFlow achieves a better utilization of space, and also more accurate flow records, without bringing extra complexity. We have implemented HashFlow, as well as several latest flow measurement algorithms such as FlowRadar, HashPipe and ElasticSketch, in a P4 software switch. Then we use traces from different operational networks to evaluate them. In these experiments, for various types of traffic analysis applications, HashFlow consistently demonstrates a clearly better performance against its state-of-the-art competitors. For example, using a small memory of 1 MB, HashFlow can accurately record around 55K flows, which is often 12.5% higher than the others. For estimating the sizes of 50K flows, HashFlow achieves a relative error of around 11.6%, while the estimation error of the best competitor is 42.9% higher. It detects 96.1% of the heavy hitters out of 250K flows with a size estimation error of 5.6%, which is 11.3% and 73.7% better than the best competitor respectively. At last, we show these merits of HashFlow come with almost no degradation of throughput.

cs.NI↗

arXiv2018

Capacity Enhanced Cooperative D2D Systems over Rayleigh Fading Channels with NOMA

This paper considers the cooperative device-to-device (D2D) systems with non-orthogonal multiple access (NOMA). We assume that the base station (BS) can communicate simultaneously with all users to satisfy the full information transmission. In order to characterize the impact of the weak channel and different decoding schemes, two kinds of decoding strategies are proposed: \emph{single signal decoding scheme} and \emph{MRC decoding scheme}, respectively. For the \emph{single signal decoding scheme}, the users immediately decode the received signals after receptions from the BS. Meanwhile, for the \emph{MRC decoding scheme}, instead of decoding, the users will keep the receptions in reserve until the corresponding phase comes and the users jointly decode the received signals by employing maximum ratio combining (MRC). Considering Rayleigh fading channels, the ergodic sum-rate (SR), outage probability and outage capacity of the proposed D2D-NOMA system are analyzed. Moreover, approximate expressions for the ergodic SR are also provided with a negligible performance loss. Numerical results demonstrate that the ergodic SR and outage probability of the proposed D2D-NOMA scheme overwhelm that of the conventional NOMA schemes. Furthermore, it is also revealed that the system performance including the ergodic SR and outage probability are limited by the poor channel condition for both the \emph{single signal decoding scheme} and conventional NOMA schemes.

cs.IT↗