SoK: Systematizing Generation, Characteristics, and Defenses in LLM-Generated Phishing
cs.CR
Submitted: 2025-08-29
Updated: 2026-08-29
Code: https://github.com/Kawaii-GPT-ai/KawaiiGPT
Project page: https://microsoft.github.io/PyRIT/api
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer
- Paladin: Defending LLM-enabled Phishing Emails with a New Trigger-Tag Paradigm
- Phishing Detection in the Gen-AI Era: Quantized LLMs vs Classical Models
- SecureNet: A Comparative Study of DeBERTa and Large Language Models for Phishing Detection
- The Impact of Emerging Phishing Threats: Assessing Quishing and LLM-generated Phishing Emails against Organizations
- How Spammers and Scammers Leverage AI-Generated Images on Facebook for Audience Growth
- Targeted Phishing Campaigns using Large Scale Language Models
- Evaluating Large Language Models' Capability to Launch Fully Automated Spear Phishing Campaigns: Validated on Human Subjects
- Spear Phishing With Large Language Models
- Teach LLMs to Phish: Stealing Private Information from Language Models
- A Persuasion-Based Prompt Learning Approach to Improve Smishing Detection through Data Augmentation
- Assessing AI vs Human-Authored Spear Phishing SMS Attacks: An Empirical Study
- Prompted Contextual Vectors for Spear-Phishing Detection
- PEEK: Phishing Evolution Framework for Phishing Generation and Evolving Pattern Analysis using Large Language Models
- Exemplifying Emerging Phishing: QR-based Browser-in-The-Browser (BiTB) Attack
- On the Feasibility of Using MultiModal LLMs to Execute AR Social Engineering Attacks
- Talking Like a Phisher: LLM-Based Attacks on Voice Phishing Classifiers
- E-PhishGen: Unlocking Novel Research in Phishing Email Detection
- Training Users Against Human and GPT-4 Generated Social Engineering Attacks
- PiMRef: Deducing Ever-evolving Spear-phishing Emails with Knowledge Base Invariants
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs