Shangsen Li

ORCID: 0000-0002-9783-388X
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Caching and Content Delivery
  • Internet Traffic Analysis and Secure E-voting
  • Network Security and Intrusion Detection
  • Opportunistic and Delay-Tolerant Networks
  • Advanced Malware Detection Techniques
  • Distributed systems and fault tolerance
  • Advanced Data Storage Technologies
  • Cloud Computing and Resource Management
  • Advanced Steganography and Watermarking Techniques
  • Cooperative Communication and Network Coding
  • Anomaly Detection Techniques and Applications
  • DNA and Biological Computing
  • Software-Defined Networks and 5G
  • Cellular Automata and Applications
  • Data Stream Mining Techniques
  • Big Data Technologies and Applications
  • Network Packet Processing and Optimization
  • Big Data and Business Intelligence
  • Network Traffic and Congestion Control

National University of Defense Technology
2020-2023

Changsha University of Science and Technology
2020

Cuckoo filter (CF) and its variants are emerging as replacements of Bloom filters in various networking distributed systems to support efficient set representation membership testing. store item fingerprints directly with two candidate buckets a reallocation scheme is implemented mitigate the bucket overflow problem for higher space utilization. Such scheme, once triggered, however, can be time-consuming. This shortcoming makes existing CFs not applicable insertion-intensive scenarios such...

10.1109/icdcs51616.2021.00015 article EN 2021-07-01

Network measurement probes the underlying network to support upper-level decisions such as management, update, maintenance, defense and beyond. Due massive, speedy, unpredictable features of flows, sketches are widely implemented in nodes approximately record frequency or estimate cardinality flows. At their cores, usually maintain one multiple counter array(s), rely on hash functions select counter(s) for each flow. Then space-efficient from distributed aggregated provide statistics...

10.48550/arxiv.2012.07214 preprint EN other-oa arXiv (Cornell University) 2020-01-01

Sketches are widely deployed to represent network flows support complex flow analysis. Typical sketches usually employ hash functions map elements into a table or bit array. Such still suffer from potential weaknesses upon throughput, flexibility, and functionality. To this end, we propose Ark filter, novel sketch that stores the element information with either of two candidate buckets indexed by quotient remainder between fingerprint filter length. In way, no further calculations required...

10.1109/tnet.2023.3263839 article EN cc-by IEEE/ACM Transactions on Networking 2023-04-13

Cuckoo filter (CF), Bloom (BF) and their variants are space-efficient probabilistic data structures for approximate set membership queries. However, synopsis would inevitably become unusable when there a number of member updates on the set; while not uncommon real-world streaming applications such as duplicate item detection, malicious URL checking, caching applications. It has been shown that some BF can be adaptive to stream current extensions generally incur unstable performance or...

10.1109/icpads53394.2021.00023 article EN 2021-12-01

Representing traffic with sketch data structures to provide flow statistics is a fundamental strategy in network measurement. In the current double-stack circumstance, we observe that IPv4 and IPv6 flows are inequivalent terms of both cardinality size Internet. The existing sketches, however, represent no differentiation. As consequence, flows, which can be massive large, while usually handful small. Such an unbalance or asymmetry feature may lead unnecessary hash collision errors,...

10.1109/lcomm.2020.3036673 article EN cc-by IEEE Communications Letters 2020-11-09

Cold data contributes a large portion of the big today and is usually stored in secondary storage. Various sketch structures are implemented to represent elements provide constant-time membership queries. Considering volume infrequent access cold data, we envision three rationales representation: 1) parallelized insertion, 2) accurate representation, 3) query/deletion. The existing sketches, however, fail achieve these simultaneously. To this end, propose novel named Parallelized cuckoo...

10.1109/hpcc-dss-smartcity-dependsys53884.2021.00055 article EN 2021-12-01

Set query is a fundamental problem in computer systems. Plenty of applications rely on the results membership, association, and multiplicity. A traditional method that addresses such derived from Bloom filter. However, methods may fail to support element deletion, require additional filters or apriori knowledge, making them unamenable high-performance implementation for dynamic set representation query. In this paper, we envision novel sketch framework multi-functional, non-parametric, space...

10.1109/tnet.2023.3247628 article EN cc-by IEEE/ACM Transactions on Networking 2023-02-24

PDF HTML XML Export Cite reminder Jump Filter: A Dynamic Sketch for Big Data Governance DOI: 10.21655/ijsi.1673-7288.00296 Author: Affiliation: Clc Number: Fund Project: Article | Figures Metrics Reference Related Cited by Materials Comments Abstract:With the rapid development of information technology, volume data maintains exponential growth, and value is hard to mine. This brings significant challenges efficient management control each link in life cycle, such as collection, cleaning,...

10.21655/ijsi.1673-7288.00296 article EN International Journal of Software and Informatics 2023-01-01

Set synchronization is a fundamental task in distributed applications and implementations. Existing methods that synchronize simple sets are mainly based on compact data structures such as Bloom filter its variants. However, these infeasible to pair of multisets which allow an element appear for multiple times. To this end, paper, we propose leverage the counting cuckoo (CCF), novel variant filter, represent thereafter multisets. The (CF) minimized hash table uses hashing resolve collisions....

10.48550/arxiv.2003.03801 preprint EN other-oa arXiv (Cornell University) 2020-01-01
Coming Soon ...