Flash crowds and denial of service attacks: characterization and implications for CDNs and web sites

By Jaeyeon Jung, Balachander Krishnamurthy, M. Rabinovich. The Web Conference, 2002

812 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications

View Paper: https://www.semanticscholar.org/paper/1a892957d2305eab30b29911cb1884bfbef369d9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Networks and Communications

Citations in the corpus

Making Scheduling "Cool": Temperature-Aware Workload Placement in Data Centers (2005, background): “Furthermore , increases in server utilization [7] [16] or the failure of a CRAC unit can upset the current environment in a matter of minutes or even seconds, requiring rapid response strategies, often faster than what is possible at a facilities level.”
Botz-4-sale: surviving organized DDoS attacks that mimic flash crowds (2005, result): “This matches Flash Crowd request rates reported in prior work [19, 20].”
Pi: a path identification mechanism to defend against DDoS attacks (2003, background): “Jung, Krishnamurthy, and Rabinovich attempt to answer the question of how a site can differentiate between a DoS attack and a simple high load condition by analyzing client request rates and file access patterns [18].”
Combining filtering and statistical methods for anomaly detection (2005, background): “, news breaking event) [9].”
SIFF: a stateless Internet flow filter to mitigate DDoS flooding attacks (2004, background): “Similarly, flash crowds exhaust the bandwidth on network links and TCP flows mutually prevent each other from achieving high bandwidth [24] (the additive increase when there is no packet loss and multiplicative decrease when there is packet loss causes TCP connections to reduce their bandwidth to a ”
SOCK: Rapid Task Provisioning with Serverless-Optimized Containers (2018, background): “A graceful reaction to ﬂash crowds [15, 22] requires concurrent low-latency deployment to many workers.”
NetCache: Balancing Key-Value Stores with Fast In-Network Caching (2017, background): “Unfortunately, the skewed, dynamic nature of real-world workloads make it difficult to provide such guarantees [2, 11, 19, 21].”
Service capacity of peer to peer networks (2004, background): “, unexpected rapid increases in the demand for particular objects, which challenge content delivery network infrastructure such as Akamai[4].”
Resilience and survivability in communication networks: Strategies, principles, and survey of disciplines (2010, background): “Traffic challenges can either be unexpected but legitimate such as from a flash crowd [48], or malicious such as from a distributed denial-ofservice (DDoS) attack [49].”
Sketch-based change detection: methods, evaluation, and applications (2003, background): “…Krishnamurthy, Subhabrata Sen, Yin Zhang Yan Chen* AT&T Labs Research; 180 Park Avenue University of California Florham Park, NJ, USA Berkeley, CA, USA {bala,sen,yzhang}@research.att.com yanchen@cs.berkeley.edu ABSTRACT Traf.c anomalies such as failures and attacks are commonplace in…”
A comprehensive survey on network anomaly detection (2018, background): “Although it is not malicious, if there is not enough time to react and provide the necessary resources to handle overload demand, these ﬂash events can seriously ﬂood or lead to complete web service failure [22,23].”
Characterization of network-wide anomalies in traffic flows (2004, methodology): “FLASH CROWD Unusually large demand for a resource/service [10].”