aiqbench analysis
This research introduces Vishing-Tactics-Bench, a novel framework that shifts voice phishing defense from post-call classification to real-time harm projection using large language models. By adapting the MITRE ATT&CK taxonomy to specific scammer utterances, the study demonstrates how LLMs can forecast exploitation trajectories to enable timely interventions before financial or data damage occurs.
Vishing-Tactics-Bench: Forecasting Exploitation Trajectories in Voice Phishing Calls
arXiv:2609.07151v1 Announce Type: new Abstract: Voice phishing (vishing) unfolds in real time; by the time a call has ended and post-hoc classification is possible, the harm has already been done. The more actionable question is which concrete harm (Information Gathering or Financial Exploitation) an ongoing call is tactically progressing toward. We present Vishing-Tactics-Bench, a benchmark grounded in Endsley's situation-awareness (SA) framework that recasts vishing defense from after-the-fact fraud classification to harm projection: predicting at each turn whether the call will reach either terminal harm. We adapt MITRE ATT&CK to vishing as a 6-tactic taxonomy (Vishing-Tactics) and label 35,340 scammer utterances across 5,645 synthetic Chinese calls. We define Exploitation Trajectory Forecasting, a survival-style protocol over the two terminal harms with three metrics: AP@k, C-index, and divergence error. Baselines ranging from a Markov heuristic to fine-tuned LLMs show that the tactical trajectory serves as an interpretable representation of the call's tactical state, supporting harm-specific forecasting, which can then be used for the downstream application of intervention selection; a stratified lead-time analysis at a tight false-alarm budget further identifies at what point in a call the trajectory signal yields early warning.
Abstract:Voice phishing (vishing) unfolds in real time; by the time a call has ended and post-hoc classification is possible, the harm has already been done. The more actionable question is which concrete harm (Information Gathering or Financial Exploitation) an ongoing call is tactically progressing toward. We present Vishing-Tactics-Bench, a benchmark grounded in Endsley's situation-awareness (SA) framework that recasts vishing defense from after-the-fact fraud classification to harm projection: predicting at each turn whether the call will reach either terminal harm. We adapt MITRE ATT&CK to vishing as a 6-tactic taxonomy (Vishing-Tactics) and label 35,340 scammer utterances across 5,645 synthetic Chinese calls. We define Exploitation Trajectory Forecasting, a survival-style protocol over the two terminal harms with three metrics: AP@k, C-index, and divergence error. Baselines ranging from a Markov heuristic to fine-tuned LLMs show that the tactical trajectory serves as an interpretable representation of the call's tactical state, supporting harm-specific forecasting, which can then be used for the downstream application of intervention selection; a stratified lead-time analysis at a tight false-alarm budget further identifies at what point in a call the trajectory signal yields early warning.
16 pages, 3 figures. Accepted to Findings of EMNLP 2026
Computation and Language (cs.CL)
arXiv:2609.07151 [cs.CL]
(or arXiv:2609.07151v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2609.07151 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 288 words
Related coverage

Article: Artificial Intelligence-Driven Phishing: How Phishing Technique Is Evolving and Implemented
InfoQ · Jun 8, 2026

Concrete Evaluations to Investigate the OpenAI Model That Hacked Hugging Face
AI Alignment Forum · Aug 3, 2026

Weekly Cybersecurity Newsletter Bulletin – Microsoft 0-day, FortiOS, PAN-OS Flaw, Revolut Data Breach, and 20+ Stories
Cybersecurity News · Sep 14, 2026
[AINews] Meta Connect 2026: Muse glasses, voice, video, and Charm
Latent Space · Sep 24, 2026