Intrusion Detection using Machine Learning Techniques: An Experimental Comparison

Kathryn-Ann Tait; Jan Sher Khan; Fehaid Alqahtani; Awais Aziz Shah; Fadia Ali Khan; Mujeeb Ur Rehman; Wadii Boulila; Jawad Ahmad

arXiv · 2105.13435

Intrusion Detection using Machine Learning Techniques: An Experimental Comparison

Kathryn-Ann Tait·Jan Sher Khan·Fehaid Alqahtani·Awais Aziz Shah·Fadia Ali Khan·Mujeeb Ur Rehman·Wadii Boulila·Jawad Ahmad

View original source ↗Read source document ↗Export metadata ↓

Abstract

Due to an exponential increase in the number of cyber-attacks, the need for improved Intrusion Detection Systems (IDS) is apparent than ever. In this regard, Machine Learning (ML) techniques are playing a pivotal role in the early classification of the attacks in case of intrusion detection within the system. However, due to a large number of algorithms available, the selection of the right method is a challenging task. To resolve this issue, this paper analyses some of the current state-of-the-art intrusion detection methods and discusses their pros and cons. Further, a review of different ML methods is carried out with four methods showing to be the most suitable one for classifying attacks. Several algorithms are selected and investigated to evaluate the performance of IDS. These IDS classifies binary and multiclass attacks in terms of detecting whether or not the traffic has been considered as benign or an attack. The experimental results demonstrate that binary classification has greater consistency in their accuracy results which ranged from 0.9938 to 0.9977, while multiclass ranges from 0.9294 to 0.9983. However, it has been also observed that multiclass provides the best results with the algorithm k-Nearest neighbor giving an accuracy score of 0.9983 while the binary classification highest score is 0.9977 from Random Forest. The experimental results demonstrate that multiclass classification produces better performance in terms of intrusion detection by specifically differentiating between the attacks and allowing a more targeted response to an attack.

Explore related subjects

cs.CR

Keep this discovery

BibTeX RIS

Kathryn-Ann Tait, Jan Sher Khan, Fehaid Alqahtani, Awais Aziz Shah, Fadia Ali Khan, Mujeeb Ur Rehman, Wadii Boulila, Jawad Ahmad. 2021-05-27. Intrusion Detection using Machine Learning Techniques: An Experimental Comparison. https://arxiv.org/abs/2105.13435

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Empirical Evaluation of Membership Inference Attacks on NLP Text Classifiers: A Baseline Study on SST-2

Membership inference attacks (MIAs) try to determine whether a specific record was used to train a model, a privacy risk that matters in natural language processing (NLP), where training data can contain sensitive user text. This paper presents a controlled benchmark of membership inference vulnerability for text classification on the GLUE SST-2 sentiment dataset. A TF-IDF + Logistic Regression pipeline and a fine-tuned DistilBERT classifier are compared under a loss-threshold MIA, with utility measured by development accuracy and macro F1. DistilBERT reached 0.9466 accuracy and 0.9460 macro F1 against 0.8756 and 0.8727 for Logistic Regression, yet both models leaked membership signal (Attack AUC 0.5615 and 0.5800, respectively). Two mitigations were tested. Stronger regularization reduced leakage for Logistic Regression at a visible utility cost, whereas fine-tuning DistilBERT for 2 epochs instead of 3 reduced leakage with negligible accuracy loss. Lightweight training adjustments can improve the privacy-utility trade-off without complex defenses.

cs.CR↗

arXiv2026

Empirical Evaluation of Data Poisoning Attacks in Supervised Learning

Data poisoning corrupts training data to degrade a model or to plant attacker-controlled behavior. This study evaluates two representative training-time attacks, label flipping and backdoor poisoning, on MNIST and Fashion-MNIST with three baseline classifiers: Logistic Regression, Linear SVM, and Random Forest. Clean training is compared with poisoning rates of 5%, 10%, and 20% using clean-test accuracy, macro-precision, macro-recall, macro-F1, and, for backdoors, attack success rate. Label flipping caused clear degradation, largest for Logistic Regression and Linear SVM, while Random Forest stayed comparatively stable. Backdoor poisoning reached attack success rates from 0.9667 to 1.0000 on both datasets and all three models while often keeping clean-test performance near baseline. The results separate indiscriminate poisoning, which shows up in standard metrics, from targeted backdoor poisoning, which stays comparatively stealthy while embedding highly effective malicious behavior, and they support security-oriented evaluation beyond conventional clean-test metrics.

cs.CR↗

arXiv2026

DeFiFusion: Combining Transaction Events with Smart Contracts to Detect Price Manipulation Attacks

Decentralized Finance (DeFi) has emerged as a rapidly growing blockchain-based financial service, where market transaction dynamics and underlying smart contract logic are intricately intertwined. This autonomous interplay, while eliminating centralized intermediaries, significantly expands the vulnerability surface of DeFi protocols to Price Manipulation Attacks (PMAs), which have already inflicted catastrophic financial losses. Despite their gravity, existing detection paradigms suffer from fundamental limitations. Transaction-centric methods lack awareness of contract execution semantics, making them prone to false positives under legitimate market volatility, while static contract analyses ignore real transaction behaviors and frequently report vulnerabilities that are infeasible to exploit in practice. We present DeFiFusion, a dual-modal PMA detection framework that closes this gap by jointly modeling transaction events and smart contract semantics within a unified pipeline. Our core insight is that PMA maliciousness emerges only from the interaction between transaction behaviors and the contract logic they exploit; neither signal suffices in isolation. Accordingly, we derive price-manipulation-aware event encoding for extracting fine-grained temporal and economic features tailored to manipulation patterns. We further introduce LLM-based contract semantic extraction to supply the execution-logic context that prior behavioral methods lack. To fuse these modalities, we propose a Dual-Modal Projection-Fusion Transformer with T5-style relative positional encoding, capturing the cyclic multi-stage execution structures that distinguish PMAs from benign market activity. Extensive experiments demonstrate that DeFiFusion consistently achieves state-of-the-art detection performance, effectively recalling 222 of the 225 PMA cases while maintaining a precision of 96.10%.

cs.CR↗