Analysis of Anomalies in the Internet Traffic Observed at the Campus Network Gateway

Veronica del Carmen Estrada

Home/Archive/arXiv

arXiv · 1706.03206

Analysis of Anomalies in the Internet Traffic Observed at the Campus Network Gateway

Veronica del Carmen Estrada

View original source ↗Read source document ↗Export metadata ↓

Abstract

A considerable portion of the machine learning literature applied to intrusion detection uses outdated data sets based on a simulated network with a limited environment. Moreover, flaws usually appear in datasets and the way we handle them may impact on measurements. Finally, the detection capacity of intrusion detection is highly influenced by the system configuration. We focus on a topic rarely investigated: the characterization of anomalies in a large network environment. Intrusion Detection System (IDS) are used to detect exploits or other attacks that raise alarms. These anomalous events usually receive less attention than attack alarms, causing them to be frequently overlooked by security administrators. However, the observation of this activity contributes to understand the traffic network characteristics. On one hand, abnormal behaviors may be legitimate, e.g., misinterpreted protocols or malfunctioning network equipment, but on the other hand an attacker may intentionally craft packets to introduce anomalies to evade monitoring systems. Anomalies found in operational network environments may indicate cases of evasion attacks, application bugs, and a wide variety of factors that highly influence intrusion detection performance. This study explores the nature of anomalies found in U-Tokyo Network using cooperatively Bro and Snort IDS among other resources. We analyze 6.5 TB of compressed binary tcpdump data representing 12 hours of network traffic. Our major contributions can be summarized in: 1) reporting the anomalies observed in real, up-to-date traffic from a large academic network environment, and documenting problems in research that may lead to wrong results due to misinterpretations of data or misconfigurations in software; 2) assessing the quality of data by analyzing the potential and the real problems in the capture process.

Explore related subjects

cs.CR

Keep this discovery

BibTeX RIS

Veronica del Carmen Estrada. 2017-06-10. Analysis of Anomalies in the Internet Traffic Observed at the Campus Network Gateway. https://arxiv.org/abs/1706.03206

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↗