BreachRadar: Automatic Detection of Points-of-Compromise

  title={BreachRadar: Automatic Detection of Points-of-Compromise},
  author={Miguel Araujo and Miguel Almeida and Jaime Ferreira and Lu{\'i}s Moura Silva and P. Bizarro},
Bank transaction fraud results in over $13B annual losses for banks, merchants, and card holders worldwide. Much of this fraud starts with a Point-of-Compromise (a data breach or a skimming operation) where credit and debit card digital information is stolen, resold, and later used to perform fraud. We introduce this problem and present an automatic Points-of-Compromise (POC) detection procedure. BreachRadar is a distributed alternating algorithm that assigns a probability of being compromised… 

Figures and Tables from this paper

Point of Compromise Detection with Unsupervised Learning
A novel method is proposed to reduce credit card fraud by identifying credit card copying points(point of compromise) where credit card data is stolen by criminals.
Communities and Anomaly Detection in Large Edged-Labeled Graphs
This work model interaction networks using appropriate matrix and tensor representations and incorporates edge attributes, such as timestamps in phone-call networks or airline codes in flight networks, and complex node side-information, in order to understand who uses a given hashtag on Twitter.


Statistical fraud detection: A review
This work describes the tools available for statistical fraud detection and the areas in which fraud detection technologies are most used, and statistics and machine learning provide effective technologies for fraud detection.
Unifying Guilt-by-Association Approaches: Theorems and Fast Algorithms
FaBP is developed, a fast algorithm that yields 2× speedup, equal or higher accuracy than BP, and is guaranteed to converge.
Spark: Cluster Computing with Working Sets
Spark can outperform Hadoop by 10x in iterative machine learning jobs, and can be used to interactively query a 39 GB dataset with sub-second response time.
Pregel: a system for large-scale graph processing
A model for processing large graphs that has been designed for efficient, scalable and fault-tolerant implementation on clusters of thousands of commodity computers, and its implied synchronicity makes reasoning about programs easier.
SocNL: Bayesian Label Propagation with Confidence
A novel algorithm is proposed that outperforms other algorithms on graphs with less smoothness and low label density and the solid theoretical foundation of the algorithm and the connections to label propagation and Bayesian inference is shown.
GraphX: a resilient distributed graph system on Spark
GraphX is introduced, which combines the advantages of both data-parallel and graph-par parallel systems by efficiently expressing graph computation within the Spark data- parallel framework and provides powerful new operations to simplify graph construction and transformation.
Some Notes on Alternating Optimization
Two new theorems that give very general local and global convergence and rate of convergence results which hold for all partitionings of x are state (without proofs).
Reducibility Among Combinatorial Problems
  • R. Karp
  • Computer Science
    50 Years of Integer Programming
  • 1972
Throughout the 1960s I worked on combinatorial optimization problems including logic circuit design with Paul Roth and assembly line balancing and the traveling salesman problem with Mike Held, which made me aware of the importance of distinction between polynomial-time and superpolynomial-time solvability.
System and method for detecting account compromises
  • US Patent US 8600872
  • 2013