AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

On the Feasibility of Using MultiModal LLMs to Execute AR Social Engineering Attacks

Ting Bi, Chenghang Ye, Zheyu Yang, Ziyi Zhou, Cui Tang, Zui Tao, Jun Zhang, Kailong Wang, Liting Zhou, Yang Yang, Tianlong Yu

AAAI 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: LLM jailbreak and injection defense · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the ReInteract social agent on top of AR + multimodal LLM (ablation)SEAR · User study experience scoreaverage experience score: 4.13 -> 4.73Improved
add multimodal LLM on top of AR only (ablation)SEAR · User study experience scoreaverage experience score: 3.33 -> 4.13Improved
add AR environment cues to basic conversation (ablation)SEAR · User study experience scoreaverage experience score: 3.03 -> 3.33Improved
full SEAR pipeline lowers variability of experience (ablation)SEAR · User study experience scorestandard deviation: 1.30 -> 0.51Improved
interaction with SEAR raises target trust in the attackerSEAR · SE effectivenessparticipants rating trust 4 or 5: 26.7% strong trust before -> 76.7% rated 4 or 5 afterImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy