Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2307.01965

An analysis of scam baiting calls: Identifying and extracting scam stages and scripts

Ian Wood·Michal Kepkowski·Leron Zinatullin·Travis Darnley·Mohamed Ali Kaafar
View original source ↗Read source document ↗Export metadata ↓

Abstract

Phone scams remain a difficult problem to tackle due to the combination of protocol limitations, legal enforcement challenges and advances in technology enabling attackers to hide their identities and reduce costs. Scammers use social engineering techniques to manipulate victims into revealing their personal details, purchasing online vouchers or transferring funds, causing significant financial losses. This paper aims to establish a methodology with which to semi-automatically analyze scam calls and infer information about scammers, their scams and their strategies at scale. Obtaining data for the study of scam calls is challenging, as true scam victims do not in general record their conversations. Instead, we draw from the community of ``scam baiters'' on YouTube: individuals who interact knowingly with phone scammers and publicly publish their conversations. These can not be considered as true scam calls, however they do provide a valuable opportunity to study scammer scripts and techniques, as the scammers are unaware that they are not speaking to a true scam victim for the bulk of the call. We applied topic and time series modeling alongside emotion recognition to scammer utterances and found clear evidence of scripted scam progressions that matched our expectations from close reading. We identified social engineering techniques associated with identified script stages including the apparent use of emotion as a social engineering tool. Our analyses provide new insights into strategies used by scammers and presents an effective methodology to infer such at scale. This work serves as a first step in building a better understanding of phone scam techniques, forming the ground work for more effective detection and prevention mechanisms that draw on a deeper understanding of the phone scam phenomenon.

Explore related subjects

cs.CR

Keep this discovery

BibTeXRIS

Ian Wood, Michal Kepkowski, Leron Zinatullin, Travis Darnley, Mohamed Ali Kaafar. 2023-07-05. An analysis of scam baiting calls: Identifying and extracting scam stages and scripts. https://arxiv.org/abs/2307.01965

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↗