Colibri

Giuliari, Giacomo; Roos, Dominik; Wyss, Marc; García-Pardo, Juan Ángel; Legner, Markus; Perrig, Adrian

doi:10.1145/3485983.3494871

Cited by 12 publications

(6 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This reconciliation of estimation accuracy and query efficiency decisively propels real-world applications that rely on stream processing. For example, emerging QoS systems based on bandwidth reservation [17] must quickly identify flows that overuse their reservation, and require the highly efficient and highly accurate flow-size estimation which only the sketches in this paper can guarantee.…”

Section: Discussionmentioning

confidence: 99%

Bayesian Sketches for Volume Estimation in Data Streams

2022

View full text Add to dashboard Cite

Given large data streams of items, each attributable to a certain key and possessing a certain volume, the aggregate volume associated with a key is difficult to estimate in a way that is both efficient and accurate. On the one hand, exact counting with dedicated counters incurs unacceptable overhead during stream processing. On the other hand, sketch algorithms, i.e., approximate-counting techniques that share counters among keys, have suffered from a trade-off between accuracy and query efficiency: Classic sketch algorithms allow to compute rough estimates in an efficient way, whereas more recent proposals yield highly accurate estimates at the cost of greatly increased computation time. In this work, we propose three sketch algorithms that overcome this trade-off, computing highly accurate estimates with lightweight procedures. To reconcile these desiderata, we employ novel estimation methods that rely on Bayesian probability theory, counter-cardinality information, and basic machine-learning techniques. The combination of these techniques enables highly accurate estimates, which we demonstrate by both a theoretical worst-case analysis and an experimental evaluation. Concretely, our sketches allow to efficiently produce volume estimates with an average relative error of < 4%, which previous methods could only achieve with computations that are several orders of magnitude more expensive.

show abstract

Section: Discussionmentioning

confidence: 99%

Bayesian Sketches for Volume Estimation in Data Streams

2022

View full text Add to dashboard Cite

show abstract

“…In the longer term, small-burst attacks might be effectively countered by DDoS defense systems that restrict flow creation. For example, COLIBRI [4] relies on source authentication and paid per-flow reservations, which limits the number of flows over which attack traffic can be distributed. Given this restriction, the adversary is forced to create medium-sized bursts in each flow, which are then again detectable.…”

Section: Discussionmentioning

confidence: 99%

“…In the mitigation component, the forwarding is adapted in order to block, rate-limit, or deprioritize the suspicious flows. Another approach is followed by COLIBRI [4], which is based on source authentication and flow-based reservations. Whenever a flow overuses its reservation, the flow is blocked.…”

Section: Problem Statement a Backgroundmentioning

confidence: 99%

“…Reservations. COLIBRI [4] maintains bandwidth reservations for a guaranteed data rate for individual flows. This data rate then constitutes the allowed base rate γ.…”

Section: Targeted Deployment Settingmentioning

confidence: 99%

“…As distributed denial-of-service (DDoS) attacks continue to plague today's Internet infrastructure, recent research has produced a range of powerful DDoS defense systems. The most prominent examples of such systems include Poseidon [1], Ripple [2], Jaqen [3], COLIBRI [4], and ACC-Turbo [5]. Such DDoS defense systems provide data-plane functionality for detection of attack traffic and mitigation of the attack, where the defense specifics are configurable by the network operator.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Low-Rate Overuse Flow Tracer (LOFT): An Efficient and Scalable Algorithm for Detecting Overuse Flows

Scherrer

Chiang

et al. 2021

2021 40th International Symposium on Reliable Distributed Systems (SRDS)

View full text Add to dashboard Cite

Current probabilistic flow-size monitoring can only detect heavy hitters (e.g., flows utilizing 10 times their permitted bandwidth), but cannot detect smaller overuse (e.g., flows utilizing 50 -100% more than their permitted bandwidth). Thus, these systems lack accuracy in the challenging environment of highthroughput packet processing, where fast-memory resources are scarce. Nevertheless, many applications rely on accurate flow-size estimation, e.g., for network monitoring, anomaly detection and Quality of Service.We design, analyze, implement, and evaluate LOFT, a new approach for efficiently detecting overuse flows that achieves dramatically better properties than prior work. LOFT can detect 1.50x overuse flows in one second, whereas prior approaches can only reliably detect flows that overuse their allocation by at least 3x. We demonstrate LOFT's suitability for high-speed packet processing with implementations in the DPDK framework and on an FPGA.

show abstract