IEEE Security and Privacy,
Vol.9, No.6, pp.36-42,
November/December, 2011.

One threat to collaborative intrusion detection systems (CIDSs) is statistic-poisoning attacks. In these attacks, adversaries inject incorrect security sensor reports to the system's repository to corrupt the published attack statistics. A novel, robust approach to computing attack statistics published by CIDSs can help counter this threat. This approach is based on contributor-level aggregation and preferential voting. In experiments, this approach effectively detected large-scale attacks and was more resistant to attacks than the basic approach.

@article{Cheung:2011:SecCIDS,
    author  = {Steven Cheung},
    title   = {Securing Collaborative Intrusion Detection Systems},
    journal = {IEEE Security and Privacy},
    volume  = {9},
    number  = {6},
    year    = {2011},
    pages   = {36-42},
    publisher = {IEEE Computer Society}
}