Corpus ID: 227254572

AugSplicing: Synchronized Behavior Detection in Streaming Tensors

@inproceedings{Zhang2021AugSplicingSB,
  title={AugSplicing: Synchronized Behavior Detection in Streaming Tensors},
  author={Jiabao Zhang and Shenghua Liu and Wenting Hou and Siddharth Bhatia and Huawei Shen and Wenjian Yu and Xueqi Cheng},
  booktitle={AAAI},
  year={2021}
}
How can we track synchronized behavior in a stream of time-stamped tuples, such as mobile devices installing and uninstalling applications in the lockstep, to boost their ranks in the app store? We model such tuples as entries in a streaming tensor, which augments attribute sizes in its modes over time. Synchronized behavior tends to form dense blocks (i.e. subtensors) in such a tensor, signaling anomalous behavior, or interesting communities. However, existing dense block detection methods are… Expand
1 Citations

Figures from this paper

Sketch-Based Streaming Anomaly Detection in Dynamic Graphs
TLDR
This paper first extends the count-min sketch data structure to a higher-order sketch, which has the useful property of preserving the dense subgraph structure, and proposes four online algorithms that utilize this enhanced data structure that detect both edge and graph anomalies. Expand

References

SHOWING 1-10 OF 35 REFERENCES
DenseAlert: Incremental Dense-Subtensor Detection in Tensor Streams
TLDR
DENSESTREAM, an incremental algorithm that maintains and updates a dense subtensor in a tensor stream, and DENSESALERT, an Incremental algorithm spotting the sudden appearances of dense subtensors are proposed. Expand
D-Cube: Dense-Block Detection in Terabyte-Scale Tensors
TLDR
D-Cube is proposed, a disk-based dense-block detection method, which also can be run in a distributed manner across multiple machines, and successfully spotted network attacks from TCP dumps and synchronized behavior in rating data with the highest accuracy. Expand
SpotLight: Detecting Anomalies in Streaming Graphs
TLDR
A randomized sketching-based approach called SpotLight is proposed, which guarantees that an anomalous graph is mapped 'far' away from 'normal' instances in the sketch space with high probability for appropriate choice of parameters. Expand
M-Zoom: Fast Dense-Block Detection in Tensors with Quality Guarantees
TLDR
This work proposes M-Zoom, a flexible framework for finding dense blocks in tensors, which works with a broad class of density measures and provides a guarantee on the lowest density of the blocks it finds. Expand
Fast Memory-efficient Anomaly Detection in Streaming Heterogeneous Graphs
TLDR
This work introduces a new similarity function for heterogeneous graphs that compares two graphs based on their relative frequency of local substructures, represented as short strings, and proposes StreamSpot, a clustering based anomaly detection approach that addresses challenges in two key fronts: heterogeneity and streaming nature. Expand
SamBaTen: Sampling-based Batch Incremental Tensor Decomposition
TLDR
SaMbaTen is introduced, a Sampling-based Batch Incremental Tensor Decomposition algorithm, which incrementally maintains the decomposition given new updates to the tensor dataset, and achieves comparable accuracy to state-of-the-art incremental and non-incremental techniques, while being 25-30 times faster. Expand
MStream: Fast Anomaly Detection in Multi-Aspect Streams
TLDR
MStream is a streaming multi-aspect data anomaly detection framework which can detect unusual group anomalies as they occur, in a dynamic manner, and outperforms state-of-the-art baselines. Expand
No Place to Hide: Catching Fraudulent Entities in Tensors
TLDR
This paper proposes an algorithm for finding multiple densest subgraphs, D-Spot, that is faster (up to 11x faster than the state-of-the-art algorithm) and can be computed in parallel and identifies dense-block detection with dense-subgraph mining, by modeling a tensor into a weighted graph without any density information lost. Expand
Real-Time Streaming Anomaly Detection in Dynamic Graphs
TLDR
This work proposes MIDAS, which focuses on detecting microcluster anomalies, or suddenly arriving groups of suspiciously similar edges, such as lockstep behavior, including denial of service attacks in network traffic data, and introduces a conditional merge step, which updates the algorithm's data structures after each time tick, to reduce the 'poisoning' effect of newly arriving edges. Expand
TimeCrunch: Interpretable Dynamic Graph Summarization
TLDR
TIMECRUNCH is an effective, scalable and parameter-free method for finding coherent, temporal patterns in dynamic graphs and is able to compress these graphs by summarizing important temporal structures and finds patterns that agree with intuition. Expand
...
1
2
3
4
...