mlsanityData to 7 Oct 2026

Exposing LLM Vulnerabilities: Adversarial Scam Detection and Performance

arXiv 2412.00621 ↗First posted 1 Dec 2024cs.CR cs.AI cs.CYcited by 4

Not on the map. Why?

Abstract (arXiv)

Can we trust Large Language Models (LLMs) to accurately predict scam? This paper investigates the vulnerabilities of LLMs when facing adversarial scam messages for the task of scam detection. We addressed this issue by creating a comprehensive dataset with fine-grained labels of scam messages, including both original and adversarial scam messages. The dataset extended traditional binary classes for the scam detection task into more nuanced scam types. Our analysis showed how adversarial examples took advantage of vulnerabilities of a LLM, leading to high misclassification rate. We evaluated the performance of LLMs on these adversarial scam messages and proposed strategies to improve their robustness.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 9 of its 19 references that are in the map. First posted on arXiv 1 Dec 2024.

Builds on

9 of 19 references.

References · 9

  1. 2019Adversarial Training for Free!cited by 638
  2. 2024Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessmentcited by 117
  3. 2023An LLM can Fool Itself: A Prompt-Based Adversarial Attackcited by 111
  4. 2023Text Classification via Large Language Modelscited by 104
  5. 2021What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Datacited by 10
  6. 2024Detecting Scams Using Large Language Modelscited by 10
  7. 2024Combating Phone Scams with LLM-based Detection: Where Do We Stand?cited by 10
  8. 2024From ML to LLM: Evaluating the Robustness of Phishing Webpage Detection Models against Adversarial Attackscited by 6
  9. 2022An Empirical Analysis of SMS Scam Detection Systemscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025TeleAntiFraud-28k: An Audio-Text Slow-Thinking Dataset for Telecom Fraud Detectioncited by 12
  2. 2026SAFE-QAQ: End-to-End Slow-Thinking Audio-Text Fraud Detection via Reinforcement Learningcited by 2
  3. 2025One Size Fits All? A Modular Adaptive Sanitization Kit (MASK) for Customizable Privacy-Preserving Phone Scam Detectioncited by 0
  4. 2025Scam Shield: Multi-Model Voting and Fine-Tuned LLMs Against Adversarial Attackscited by 0