Abstract: An improved network protocol for mitigating network amplification attacks is provided. The absolute network load that any transient distributed attack can cause is bounded based on a resource crediting scheme. The protocol accumulates “credit” upon reception and detection of candidate attack request packets, and draws against that credit when transmitting responsive packets. In some implementations, the time frame of such an attack is also bounded using time limits applied to a resource crediting scheme. Other resources may also be bounded by the resource crediting scheme, including without limitation CPU utilization, storage capacity, power, etc.

Abstract: An improved network protocol for mitigating network amplification attacks is provided. The absolute network load that any transient distributed attack can cause is bounded based on a resource crediting scheme. The protocol accumulates “credit” upon reception and detection of candidate attack request packets, and draws against that credit when transmitting responsive packets. In some implementations, the time frame of such an attack is also bounded using time limits applied to a resource crediting scheme. Other resources may also be bounded by the resource crediting scheme, including without limitation CPU utilization, storage capacity, power, etc.

Abstract: An improved network protocol for mitigating network amplification attacks is provided. The absolute network load that any transient distributed attack can cause is bounded based on a resource crediting scheme. The protocol accumulates “credit” upon reception and detection of candidate attack request packets, and draws against that credit when transmitting responsive packets. In some implementations, the time frame of such an attack is also bounded using time limits applied to a resource crediting scheme. Other resources may also be bounded by the resource crediting scheme, including without limitation CPU utilization, storage capacity, power, etc.

Abstract: Various actively probing techniques on a network allow an estimation of the sustainable capacity available in the network. One implementation probes the network using two probe sequences having different loads. Probe estimates associated with each sequence are used to estimate the sustainable capacity in the network. Another implementation probes the network using two probe sequences, in which either the probe packet size or the inter-probe gap are different between the sequences. Calculation of a delay trend for each sequence leads to estimate of the maximum network capacity and the background load on the network. Yet another implementation uses a windowing technique to probe the sustainable capacity in the network. The window size is increased until the network is saturated. The number of bytes transferred within the window during a given time period is an estimate of the sustainable capacity of the network.

Abstract: Real time communications over a network are adjusted to improve the quality of service (QoS) under incipient congestion conditions. The system detects incipient network congestion and feeds back information regarding the incipient congestion back to the transmitter. Based on this information, the transmission rate is altered appropriately using a control algorithm, which computes the altered transmission rate based on a weight parameter, a gain parameter, and information from a congestion report. The altered transmission rate improves the transmitter's use of the available bandwidth to maintain an acceptable QoS at the receiver.

Abstract: Various actively probing techniques on a network allow an estimation of the sustainable capacity available in the network. One implementation probes the network using two probe sequences having different loads. Probe estimates associated with each sequence are used to estimate the sustainable capacity in the network. Another implementation probes the network using two probe sequences, in which either the probe packet size or the inter-probe gap are different between the sequences. Calculation of a delay trend for each sequence leads to estimate of the maximum network capacity and the background load on the network. Yet another implementation uses a windowing technique to probe the sustainable capacity in the network. The window size is increased until the network is saturated. The number of bytes transferred within the window during a given time period is an estimate of the sustainable capacity of the network.

Abstract: Real time communications over a network are adjusted to improve the quality of service (QoS) under incipient congestion conditions. The system detects incipient network congestion and feeds back information regarding the incipient congestion back to the transmitter. Based on this information, the transmission rate is altered appropriately using a control algorithm, which computes the altered transmission rate based on a weight parameter, a gain parameter, and information from a congestion report. The altered transmission rate improves the transmitter's use of the available bandwidth to maintain an acceptable QoS at the receiver.