ONE-Geo: Client-Independent IP Geolocation Based on Owner Name Extraction

Wang, Yucheng; Wang, Xu; Zhu, Hongsong; Zhang, Hai; Li, Hong; Sun, Limin

doi:10.1007/978-3-030-23597-0_28

Cited by 7 publications

(23 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…IP after the probing host [2] obtains the measurement data (e.g., delay) to the target IP and landmarks [2,5]. Landmarks are IP addresses with known locations [2].…”

Section: Measurement-based Ip Geolocation Can Geolocate a Targetmentioning

confidence: 99%

“…Generally, existing measurement-based fine-grained IP geolocation methods can be categorized into two kinds: rule-based and deep learning-based methods (referred as learning-based methods in this paper). For rule-based methods like SLG [5] and Corr-SLG [2], they assume that most hosts in one computer network are following some delay-distance rules. These hypothetical rules are proposed by human experts based on their observations.…”

Section: Measurement-based Ip Geolocation Can Geolocate a Targetmentioning

confidence: 99%

“…The median error distances of fine-grained IP geolocation methods are usually less than 10 kilometers. Though there are several finegrained IP geolocation methods like SLG [5], Checkin-geo [6], Corr-SLG [2] and MLP-Geo [7], they stills face many challenging problems. In this paper, we mainly focus on improving the generalization capabilities of measurement-based fine-grained IP geolocation in different computer networks.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

GNN-Geo: A Graph Neural Network-based Fine-grained IP geolocation Framework

Ding¹,

Luo²,

Wang

et al. 2023

IEEE Trans. Netw. Sci. Eng.

View full text Add to dashboard Cite

Rule-based fine-grained IP geolocation methods are hard to generalize in computer networks which do not follow hypothetical rules. Recently, deep learning methods, like multi-layer perceptron (MLP), are tried to increase generalization capabilities. However, MLP is not so suitable for graph-structured data like networks. MLP treats IP addresses as isolated instances and ignores the connection information, which limits geolocation accuracy. In this work, we research how to increase the generalization capability with an emerging graph deep learning method -Graph Neural Network (GNN). First, IP geolocation is re-formulated as an attributed graph node regression problem. Then, we propose a GNN-based IP geolocation framework named GNN-Geo. GNN-Geo consists of a preprocessor, an encoder, messaging passing (MP) layers and a decoder. The preprocessor and encoder transform measurement data into the initial node embeddings. MP layers refine the initial node embeddings by modeling the connection information. The decoder maps the refined embeddings to nodes' locations and relieves the convergence problem by considering prior knowledge. The experiments in 8 real-world IPv4/IPv6 networks in North America, Europe and Asia show the proposed GNN-Geo clearly outperforms the state-of-art rule-based and learning-based baselines. This work verifies the great potential of GNN for fine-grained IP geolocation.

show abstract

“…IP after the probing host [2] obtains the measurement data (e.g., delay) to the target IP and landmarks [2,5]. Landmarks are IP addresses with known locations [2].…”

Section: Measurement-based Ip Geolocation Can Geolocate a Targetmentioning

confidence: 99%

Section: Measurement-based Ip Geolocation Can Geolocate a Targetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

GNN-Geo: A Graph Neural Network-based Fine-grained IP geolocation Framework

Ding¹,

Luo²,

Wang

et al. 2023

IEEE Trans. Netw. Sci. Eng.

View full text Add to dashboard Cite

show abstract

“…Certainly, these are some other methods to identify owners. AIWEN [8], a commercial company, and Wang [9] extract the owners of domains by regex rules such as "Copyright@ (.+?)." But that kind of methods only uses the websites instead of heterogeneous data of devices, resulting in low accuracy and coverage.…”

Section: Related Workmentioning

confidence: 99%

“…Seeds share the same idea as researches [8,9] in Related Work section. It can be concluded from Table 4 that the method used in this paper can achieve a relatively high coverage rate of 28.90% under the premise of ensuring a certain accuracy of 74.20% with the randomly selected 1000 samples in the real environment.…”

Section: Community Recognitionmentioning

confidence: 99%

Understanding User-Level IP Blocks on the Internet

Ren

et al. 2022

Security and Communication Networks

Self Cite

View full text Add to dashboard Cite

Generally, the devices on the Internet are identified by IP addresses. The users of IPs are those who use IPs on the Internet and are always different from their registers and operators. Since IPs are used as unique identifiers of devices, knowing users of IPs according to their multisource data is critical for experts to protect the security of the network. At present, there are only few methods to mine the users of IPs from their public data. To make matters worse, the existing methods do not make effective use of a large amount and multisource data, such as certificates, protocol banner, rDNS, location, topology, etc. As a result, the performances of existing methods are largely limited. To tackle this issue, we proposed ULIB, short for “Understanding User-Level IP Blocks on the Internet.” ULIB is based on improved community detection to mine the users for as many blocks of IPs as possible. By analysing comprehensive attributes of IPs, ULIB is able to recognize users effectively. Meanwhile, we evaluated our methodology in the real world and the experiments demonstrated that the accuracy of ULIB is 74.20% and the coverage is 28.90% in a city of China, which outperforms other existing methods.

show abstract

Discover the ICS Landmarks Based on Multi-stage Clue Mining

Liu

Wang

et al. 2022

Wireless Algorithms, Systems, and Applications

View full text Add to dashboard Cite

ONE-Geo: Client-Independent IP Geolocation Based on Owner Name Extraction

Cited by 7 publications

References 12 publications

GNN-Geo: A Graph Neural Network-based Fine-grained IP geolocation Framework

GNN-Geo: A Graph Neural Network-based Fine-grained IP geolocation Framework

Understanding User-Level IP Blocks on the Internet

Discover the ICS Landmarks Based on Multi-stage Clue Mining

Contact Info

Product

Resources

About