A novel hierarchical parallelism for accelerating NIDS using GPUs | Semantic Scholar (2025)

This paper presents a novel hybrid pattern matching algorithm that efficiently exploits the computing power of a heterogeneous system composed of multicore processors and multiple graphics processing units (GPUs).

A pattern matching algorithm that exploits the full computational power of Intel Xeon Phi processors by using both SIMD and thread parallelism and reveals that both parallelism methods provide performance gains.

Reinhardt represents regex patterns as a combination of reconfigurable cells in hardware and updates regex patterns in real-time while providing high performance, and can operate as NIDS/NIPS and as the REM accelerator for them.

It is concluded that due to computational complexity and slow hardware processing capabilities of Wi-Fi Pineapple, it could not become suitable IDS in the presence of different pattern matching strategies and a modification of Snort is proposed to increase the throughput of the system.

A carefully designed taxonomy highlighting eight main challenges and solutions is presented and common datasets from 1999 to 2020 are explored and future directions are proposed on expanding NID into cloud-based environments, devising scalable models for larger amount of network intrusion data, and creating labeled datasets collected in real-world networks.

The review paper aims to give a brief idea of what's a network and its related security issues especially about passive attacks and how to detect and prevent them, by using the existing methods and tools available.

Several techniques are introduced to do optimization on GPUs, including reducing global memory transactions of input buffer, reducing latency of transition table lookup, eliminating output table accesses, avoiding bank-conflict of shared memory, coalescing writes to global memory, and enhancing data transmission via peripheral component interconnect express.

Two parallel string matching algorithms which adopt perfect hashing to compact a state transition table are proposed which reduce up to 99.5 percent memory requirements for storing the state Transition table compared to the traditional two-dimensional memory architecture.

An intrusion detection system based on the Snort open-source NIDS that exploits the underutilized computational power of modern graphics cards to offload the costly pattern matching operations from the CPU, and thus increase the overall processing throughput.

A modular design of parallel NIDS based on Snort, named Para-Snort, that enables flexible and easy module design and the performance impact of load balancing and multi-pattern matching is analyzed.

This work presents a methodology for system-wide integration of graph-based partitioning of large intrusion detection pattern databases that yields designs with competitive clock frequencies that are a minimum of 8x more area efficient than previous non-predecoded shift-and-compare architectures.

A novel memory architecture using perfect hashing to condense state transition tables without hash collisions is proposed, which achieves up to 99.5% improvement in memory reduction compared to the traditional two-dimensional memory architecture.

This paper details the implementation of hardware based regular expression engines for the SNORT IDS by transforming the PCRE opcodes generated by the PCre compiler from SNORT regular expression rules, and implements a regular expression only once for each new rule in theSNORT ruleset, thus resulting in a fast system that scales well with new updates.

A simple, efficient algorithm to locate all occurrences of any of a finite number of keywords in a string of text that has been used to improve the speed of a library bibliographic search program by a factor of 5 to 10.