Jiang Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jiang Li has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Jiahao Cao
Tsinghua University
5 shared publications - Mingwei Xu
Tsinghua University, Beijing, China
5 shared publications - Yangyang Wang
Tsinghua University, Beijing, China
3 shared publications - Renjie Xie
Guilin University of Electronic Technology, Guilin, China
2 shared publications - Changliyun Liu1 shared publication
- Junrui Xu1 shared publication
Latest Publications
- 17 December 2025
- Published by Elsevier in Computers & Security
- Vol. 162
A large-scale measurement study of region-based web access restrictions: The case of China
- 17 December 2025
- Published by Elsevier in Computers & Security
- Vol. 162
A large-scale measurement study of region-based web access restrictions: The case of China
- Open Access
- 8 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 19-21
Fuzzing RPKI Validators with Semantic and Structural Awareness
- 8 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 19-21
Open AccessFuzzing RPKI Validators with Semantic and Structural Awareness
- Open Access
- 6 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 87-92
Assessing the Impact of ISP de-peering: A case study of Cogent’s Disconnection from Russian Networks in Routing Perspective
- 6 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 87-92
Open AccessAssessing the Impact of ISP de-peering: A case study of Cogent’s Disconnection from Russian Networks in Routing Perspective
- Open Access
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 4970-4972
Poster: Few-Shot Inter-Domain Routing Threat Detection with Large-Scale Multi-Modal Pre-Training
Border Gateway Protocol (BGP) plays a pivotal role as the de facto inter-domain routing protocol on the Internet. However, BGP threats continually emerge and undermine the Internet reliability. Existing BGP threat detection methods based on machine learning require substantial labeled data and expert involvement, making them costly and labor-intensive. Moreover, they fail to learn rich information from massive unlabeled BGP data consistently generated on the Internet. In this paper, we propose FIRE that enables few-shot inter-domain routing threat detection with large-scale multi-modal pre-training. FIRE conducts domain-specific pre-training tasks to acquire rich BGP implicit knowledge from massive unlabeled BGP data for few-shot learning. Our experiments show that FIRE can be fine-tuned to precisely identify BGP threats with only a few labeled samples, e.g., a 93.2% precision in route leak detection with merely 8 events for fine-tuning.
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 4970-4972
Open AccessPoster: Few-Shot Inter-Domain Routing Threat Detection with Large-Scale Multi-Modal Pre-Training
Border Gateway Protocol (BGP) plays a pivotal role as the de facto inter-domain routing protocol on the Internet. However, BGP threats continually emerge and undermine the Internet reliability. Existing BGP threat detection methods based on machine learning require substantial labeled data and expert involvement, making them costly and labor-intensive. Moreover, they fail to learn rich information from massive unlabeled BGP data consistently generated on the Internet. In this paper, we propose FIRE that enables few-shot inter-domain routing threat detection with large-scale multi-modal pre-training. FIRE conducts domain-specific pre-training tasks to acquire rich BGP implicit knowledge from massive unlabeled BGP data for few-shot learning. Our experiments show that FIRE can be fine-tuned to precisely identify BGP threats with only a few labeled samples, e.g., a 93.2% precision in route leak detection with merely 8 events for fine-tuning.
- 24 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Networking
- Vol. 32 (6) , 5263-5278
RoLL+: Real-Time and Accurate Route Leak Locating With AS Triplet Features at Scale
Border Gateway Protocol (BGP) is the only inter-domain routing protocol that plays an important role on the Internet. However, BGP suffers from route leaks, which can cause serious security threats. To mitigate the effects of route leaks, accurate and timely route leak locating is of great importance. Prior studies leverage AS business relationships to locate route leaks in real time. However, they fail to achieve high locating accuracy. Recent studies apply machine learning to accurately detect route leaks from statistical features of massive BGP messages. Nevertheless, they have high detection latency and cannot further locate route leaks. In this paper, we propose a real-time and accurate route leak locating system named 1.. It leverages distinctive AS triplet features to accurately locate AS triplets with route leaks from each BGP message in real time. Considering that 2. may receive a substantial volume of BGP update messages per second, we integrate a cache-like design and a lazy update mechanism into the system to effectively identify route leaks at scale. Our experimental results on real-world BGP route leak data demonstrate that it can achieve 92% locating accuracy with less than 1 ms locating latency. Furthermore, the results show that 3. can process over 7,000 AS triplets per second, meeting real-world throughput requirements.
- 24 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Networking
- Vol. 32 (6) , 5263-5278
RoLL+: Real-Time and Accurate Route Leak Locating With AS Triplet Features at Scale
Border Gateway Protocol (BGP) is the only inter-domain routing protocol that plays an important role on the Internet. However, BGP suffers from route leaks, which can cause serious security threats. To mitigate the effects of route leaks, accurate and timely route leak locating is of great importance. Prior studies leverage AS business relationships to locate route leaks in real time. However, they fail to achieve high locating accuracy. Recent studies apply machine learning to accurately detect route leaks from statistical features of massive BGP messages. Nevertheless, they have high detection latency and cannot further locate route leaks. In this paper, we propose a real-time and accurate route leak locating system named 1.. It leverages distinctive AS triplet features to accurately locate AS triplets with route leaks from each BGP message in real time. Considering that 2. may receive a substantial volume of BGP update messages per second, we integrate a cache-like design and a lazy update mechanism into the system to effectively identify route leaks at scale. Our experimental results on real-world BGP route leak data demonstrate that it can achieve 92% locating accuracy with less than 1 ms locating latency. Furthermore, the results show that 3. can process over 7,000 AS triplets per second, meeting real-world throughput requirements.