# The Shadow of Fraud: The Emerging Danger of AI-powered Social Engineering and its Possible Cure

arXiv: https://arxiv.org/abs/2407.15912 · HTML: https://mlsanity.com/paper/2407.15912/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jul 2024.

## Built on by (most cited first, 5 of 5)

- [TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems](https://mlsanity.com/paper/2506.04133/) (2025)
- [DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarios](https://mlsanity.com/paper/2510.15501/) (2025)
- [Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Models](https://mlsanity.com/paper/2412.17128/) (2024)
- [Self-Sovereign Agent](https://mlsanity.com/paper/2604.08551/) (2026)
- [Red Teaming with Artificial Intelligence-Driven Cyberattacks: A Scoping Review](https://mlsanity.com/paper/2503.19626/) (2025)

## Abstract (arXiv)

Social engineering (SE) attacks remain a significant threat to both individuals and organizations. The advancement of Artificial Intelligence (AI), including diffusion models and large language models (LLMs), has potentially intensified these threats by enabling more personalized and convincing attacks. This survey paper categorizes SE attack mechanisms, analyzes their evolution, and explores methods for measuring these threats. It highlights the challenges in raising awareness about the risks of AI-enhanced SE attacks and offers insights into developing proactive and adaptable defense strategies. Additionally, we introduce a categorization of the evolving nature of AI-powered social engineering attacks into "3E phases": Enlarging, wherein the magnitude of attacks expands through the leverage of digital media; Enriching, introducing novel attack vectors and techniques; and Emerging, signifying the advent of novel threats and methods. Moreover, we emphasize the necessity for a robust framework to assess the risk of AI-powered SE attacks. By identifying and addressing gaps in existing research, we aim to guide future studies and encourage the development of more effective defenses against the growing threat of AI-powered social engineering.