cs.CRNov 5, 2026

Toward Safety-Aware AI Agents in Realistic Social Engineering Attack Scenarios

Authors: Zhitao He, Chengru Han, Chi Him Zhang, Yi R Fung

Organizations: MMSense Lab, The Hong Kong University of Science and Technology

Abstract

Personal AI agents are increasingly deployed on user devices to execute actions involving real money and sensitive data, but their security under social engineering attacks has not been systematically evaluated. We propose SEA (Social Engineering Attack Benchmark), the first interactive environment for evaluating the intrinsic security capability of AI agents in social engineering attack scenarios, covering 8 daily-life domains, 30+ simulated applications, a 4-level difficulty gradient, and a 5-dimensional evaluation framework, with 320 evaluation tasks designed in consultation with anti-fraud specialists and spanning two culturally distinct settings in Chinese and English. Evaluation on 11 frontier open-source and closed-source models, with GPT-6 evaluated only in Chinese, reveals that all models are breached to varying degrees (Chinese attack success rates ranging from 16.9% to 84.3%) proactive verification rates universally below 32%. We further propose META-SEA, a co-evolutionary framework for attack tasks and defenders. With META-SEA training, Qwen3-8B achieves defense performance comparable to closed-source models while effectively reducing ungrounded action claims.

Figures & tables

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Nov 5, 2026

Multimodal-SEA: Benchmarking AI Agent Security under Multimodal Social Engineering Attacks

Personal AI agents face social engineering attacks supported by forged multimodal content, but existing evaluations mainly focus on text-based dialogue, leaving their intrinsic security under such attacks insufficiently studied. We introduce Multimodal-SEA, an interactive benchmark comprising 608 expert-designed tasks grounded in real-world fraud cases, covering 14 domains and 152 attack scenarios with prepared multimodal content. The tasks span four difficulty levels and reflect the distinct social and cultural contexts of Chinese and English environments. Agents inspect content, verify requests, and execute actions in simulated applications, with attack outcomes grounded in verifiable tool execution logs. To enable controlled red teaming of personal agents, we design a multimodal attack harness that integrates task information, attack progression control, and multimodal content construction to evaluate their intrinsic security against adaptive social engineering attacks in simulated environments. Evaluating seven widely used multimodal models across six dimensions reveals that all are vulnerable, with attack success rates of 7.1% to 34.5%. Adding multimodal content increases attack success from 19.9% to 29.2%, despite increased proactive verification coverage. Stronger safety instructions reduce attack success without improving recognition of deceptive multimodal content, while lower attack success rates for some models accompany excessive refusal of legitimate requests.
Oct 24, 2026

Agent-to-Agent Synthetic Social Engineering on the Web

An AI agent can prepare an accurate report and still request an action its user has not authorized. Cooperation across Web services therefore requires separate judgments about identity, evidentiary support, and permission. We define synthetic social engineering (SSE) as deliberately deceptive or misleading influence intended to exploit AI recipients' responses to credibility, authority, or obligation cues and redirect behavior away from authorized objectives. We focus on separately tasked sender agents that produce or adapt misleading communication. Drawing on cybersecurity, social engineering, and persuasion research, we develop an operational framework connecting actors, deceptive representations, candidate influence routes, evidence or permission boundaries, responses, and consequences. The framework distinguishes attempts from successful redirection, without assuming human psychological processes. We implement it in the Agent Service Exchange and Evidence Commons (ASE-EC), a reproducible testbed with independently specified records and authorization scopes. Across 1,260 research episodes using Qwen3-4B in two fictional briefing tasks, matched comparisons test authority and commitment appeals, while defense comparisons assess protection alongside authorized task completion. Invoking a limited prior agreement increased unauthorized requests from 43.3% to 96.7%, although recipients retained supported decisions and permissions remained unchanged. These controlled findings identify action selection as a distinct security concern, even when evidence handling succeeds, and they provide a reusable basis for evaluating safeguards that preserve useful cooperation across Web services.
Aug 10, 2026

Beyond Detection: Evaluating Defensive LLMs Against AI-Generated Social Engineering in Live Turn-by-Turn Interaction

Generative AI makes social-engineering attacks more fluent, adaptive, and scalable, increasing the need for LLM-based de- fenders that can protect users during ongoing interactions. We ask whether such defenders identify the structural source of risk or merely react to surface cues. We formalize trust-chain localization: identifying whether an interaction fails at actor authority, asset control, verification sufficiency, or transaction path. We construct a controlled 300-case online-housing corpus spanning 20 scenario families, legitimate cases, four structural failure modes, and three surface conditions. Five defender models are evaluated on the same corpus in state- ful turn-by-turn and one-shot static settings, yielding 1,500 model-case evaluations per protocol and 3,000 in total. No model produced explicit unsafe compliance, yet defensive effectiveness varied sharply: intervention rates ranged from 0% to 96.3%. Protective action and correct structural localization were frequently decoupled, with models sometimes intervening while identifying the wrong trust component or recognizing a structural failure without taking protective action. Asset-control failures were a major localization bottleneck, surface sensitivity varied across models, and live-static differences were model-dependent. These findings show that safe-looking behavior alone is insufficient; live scam resistance must separately measure intervention, timing, structural localization, and false-positive behavior.