Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels | Paper Citation Record

Observation 310a5515-6355-416c-8f2e-ef6ed69bc748 · outbound

This paper cites ‘hey mum, i dropped my phone down the toilet’: Investigating hi mum and dad sms scams in the united kingdom.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels ‘hey mum, i dropped my phone down the toilet’: Investigating hi mum and dad sms scams in the united kingdom

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:37.173387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 699ba449-4c43-40a0-8492-1bd65da38e0e · outbound

This paper cites Dissect- ing ghost clicks: Ad fraud via misdirected human clicks.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Dissect- ing ghost clicks: Ad fraud via misdirected human clicks

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:37.286007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a4ffbcf-013a-404a-8ce1-addc73b53173 · outbound

This paper cites AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:37.405911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4eebf578-7e29-4bd9-9a67-81dff3c95de1 · outbound

This paper cites Alipay.https://www.alipay.com/.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Alipay.https://www.alipay.com/

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:37.458396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 769a3e91-46c6-4a37-8bae-a21760946667 · outbound

This paper cites Malvertising in facebook: Analysis, quan- tification and solution.Electronics, 9(8):1332, 2020.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Malvertising in facebook: Analysis, quan- tification and solution.Electronics, 9(8):1332, 2020

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:37.586404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b42fbd9b-b91c-4bfc-b6bf-c196b246aecf · outbound

This paper cites Click-fraud monetizing malware: A survey and case study.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Click-fraud monetizing malware: A survey and case study

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:37.659433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9883fca-74ed-41df-ad2e-2ea9cc0eb131 · outbound

This paper cites Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:37.731914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd2d9a99-948e-4d09-a1d3-46ae37c93dbe · outbound

This paper cites Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901, 2020.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901, 2020

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:37.808700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a3961a7-4288-4339-9d70-9cb4c9a0a79c · outbound

This paper cites A large scale study of user be- havior, expectations and engagement with android permissions.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels A large scale study of user be- havior, expectations and engagement with android permissions

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:37.820896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afc194ca-50ce-4f15-b2c8-45761eb90adf · outbound

This paper cites Spa-bench: A comprehensive benchmark for smartphone agent evaluation.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Spa-bench: A comprehensive benchmark for smartphone agent evaluation

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:37.865995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97d1c926-8515-46b4-8a4b-58af8219a60e · outbound

This paper cites StruQ: Defending Against Prompt Injection with Structured Queries.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels StruQ: Defending Against Prompt Injection with Structured Queries

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:37.935210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9091b94-22eb-48b4-8f30-978e86cc66db · outbound

This paper cites Bifocals: Analyzing webview vulnerabilities in android applications.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Bifocals: Analyzing webview vulnerabilities in android applications

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:37.956001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e908770b-f620-4839-a470-3d5f8b1920ed · outbound

This paper cites An empirical study of click fraud in mobile ad- vertising networks.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels An empirical study of click fraud in mobile ad- vertising networks

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:37.966247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa552caf-104e-48b6-8fff-e155093c02f6 · outbound

This paper cites Madfraud: Investigating ad fraud in android applications.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Madfraud: Investigating ad fraud in android applications

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:37.989989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 699d9ddf-8fff-4638-8a05-83a5233affbb · outbound

This paper cites Advancing mobile gui agents: A verifier-driven approach to practical deployment.arXiv preprint arXiv:2503.15937, 2025.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Advancing mobile gui agents: A verifier-driven approach to practical deployment.arXiv preprint arXiv:2503.15937, 2025

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.000471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc959d86-7914-4a3f-92e4-a961064ba38b · outbound

This paper cites Defeating Prompt Injections by Design.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Defeating Prompt Injections by Design

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.002885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7305b20a-4194-4769-b0a5-6859adf43956 · outbound

This paper cites Agent- dojo: A dynamic environment to evaluate attacks and defenses for llm agents.arXiv e-prints, pages arXiv–2406, 2024.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Agent- dojo: A dynamic environment to evaluate attacks and defenses for llm agents.arXiv e-prints, pages arXiv–2406, 2024

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.005564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcb273dc-49b8-4a6d-ba7d-90cd7f6f5ee0 · outbound

This paper cites Delgado-Soto, J.E.L.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Delgado-Soto, J.E.L

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.007481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf108a2c-87a1-4d0e-ac04-6a3bfc2e3c92 · outbound

This paper cites Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.009250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03cd65a9-4301-4b7d-87f6-ad55c6a55a51 · outbound

This paper cites Fossify notes beta.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Fossify notes beta

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.011496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1c35412-5d4c-4fc8-ac02-d46d2beeeee5 · outbound

This paper cites Fraud- droid: Automated ad fraud detection for android apps.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Fraud- droid: Automated ad fraud detection for android apps

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.013294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 804d0b1e-c747-4dee-8974-c5897a8032b1 · outbound

This paper cites Why eve and mal- lory love android: An analysis of android ssl (in) security.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Why eve and mal- lory love android: An analysis of android ssl (in) security

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.015242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18322551-6a8b-457e-926c-7323c6fe4b79 · outbound

This paper cites Not what you’ve signed up for: Compromising real-world llm-integrated ap- plications with indirect prompt injection.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Not what you’ve signed up for: Compromising real-world llm-integrated ap- plications with indirect prompt injection

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.017253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04424b68-ee78-4b48-a29d-d030d565ed77 · outbound

This paper cites Defending against phishing attacks: taxonomy of methods, cur- rent issues and future directions.Telecommunication Systems, 67(2):247–267, 2018.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Defending against phishing attacks: taxonomy of methods, cur- rent issues and future directions.Telecommunication Systems, 67(2):247–267, 2018

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.019243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e790620-dd76-45dd-a521-fbb54978512f · outbound

This paper cites Medusa attack: Exploring security hazards of {in- app}{QR} code scanning.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Medusa attack: Exploring security hazards of {in- app}{QR} code scanning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.021134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dde38284-d17b-4cf9-a32c-f02a3dd3d49f · outbound

This paper cites Securing llm systems against prompt injec- tion.Online], https://developer.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Securing llm systems against prompt injec- tion.Online], https://developer

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.022997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99aee33e-018c-48ee-af4e-a307b05b5173 · outbound

This paper cites OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.024864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b35ec04-0d94-4e8d-b232-badedc26f76b · outbound

This paper cites TrustAgent: Towards Safe and Trustworthy LLM-based Agents.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels TrustAgent: Towards Safe and Trustworthy LLM-based Agents

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.027003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e6398dc-a637-4733-a6e0-2f75f01a1e29 · outbound

This paper cites ileakage: browser-based timerless speculative execu- tion attacks on apple devices.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels ileakage: browser-based timerless speculative execu- tion attacks on apple devices

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.029117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc260061-43e6-4363-b407-5ae756be8242 · outbound

This paper cites an unresolved cited work.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.031025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c50f0a73-6ec3-451d-93d6-fc8011508c09 · outbound

This paper cites Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.033013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 911e5dc9-49d3-44b4-92db-cc9c66b639e4 · outbound

This paper cites Deep learning.nature, 521(7553):436–444, 2015.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Deep learning.nature, 521(7553):436–444, 2015

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.035761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f4dad8d-5910-450d-b5f5-65e786669759 · outbound

This paper cites sudo rm -rf agentic_security.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels sudo rm -rf agentic_security

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.037639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 210a4307-8758-4608-ac59-fb2f5a9acbd7 · outbound

This paper cites Don’t kill my ads! balancing privacy in an ad-supported mobile application market.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Don’t kill my ads! balancing privacy in an ad-supported mobile application market

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.040014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e36b5551-e79c-4033-9e44-68fbdd28bc08 · outbound

This paper cites Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.041872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation beac10fb-3bc2-42ca-8322-1fe362c96b88 · outbound

This paper cites Knowing your enemy: understanding and detecting malicious web advertising.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Knowing your enemy: understanding and detecting malicious web advertising

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.043896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6ff12cc-cb1e-4b67-9f72-282fd2f18fdd · outbound

This paper cites {DECAF}: Detecting and characterizing ad fraud in mobile apps.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels {DECAF}: Detecting and characterizing ad fraud in mobile apps

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.045705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e6c2a87-6315-4465-837a-8113aa7ede74 · outbound

This paper cites Maddroid: Characterizing and detecting devious ad contents for android apps.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Maddroid: Characterizing and detecting devious ad contents for android apps

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.047700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e87b3f56-3e5a-4b8f-909d-9501f9c5527d · outbound

This paper cites an unresolved cited work.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Unresolved cited work

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.050185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c07a228-5615-42d9-88b4-b5175bdfd3ff · outbound

This paper cites Formalizing and benchmarking prompt injection attacks and defenses.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Formalizing and benchmarking prompt injection attacks and defenses

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.052124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca4b09a4-c7c3-4696-a862-1dc80ce817fd · outbound

This paper cites Agen- trewardbench: Evaluating automatic evaluations of web agent trajectories.arXiv preprint arXiv:2504.08942, 2025.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Agen- trewardbench: Evaluating automatic evaluations of web agent trajectories.arXiv preprint arXiv:2504.08942, 2025

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.054066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30373810-42a6-40ba-924e-099ccc24dee6 · outbound

This paper cites Careful About What App Promotion Ads Recommend! Detecting and Explaining Malware Promotion via App Promotion Graph.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Careful About What App Promotion Ads Recommend! Detecting and Explaining Malware Promotion via App Promotion Graph

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.055973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c23c29b1-f0d1-467f-a850-c81adff2cc90 · outbound

This paper cites When advertising turns nasty.Net- work Security, 2015(11):5–8, 2015.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels When advertising turns nasty.Net- work Security, 2015(11):5–8, 2015

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.058145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa287ee1-605e-462a-8647-772a7aa7f3c0 · outbound

This paper cites A Study of MAC Address Randomization in Mobile Devices and When it Fails.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels A Study of MAC Address Randomization in Mobile Devices and When it Fails

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.060137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0afa7e6-7665-4908-970f-08ef33fb8777 · outbound

This paper cites The price of free: Privacy leakage in personalized mobile in-apps ads.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels The price of free: Privacy leakage in personalized mobile in-apps ads

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.062410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcf5328f-4e73-460e-be55-bc68304fa976 · outbound

This paper cites Whatsapp.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Whatsapp

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.064248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef328913-b292-42b3-83ef-511f21018122 · outbound

This paper cites What’s clicking what? techniques and innova- tions of today’s clickbots.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels What’s clicking what? techniques and innova- tions of today’s clickbots

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.066347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a163b47-e7da-491e-9eeb-e80097ff3d55 · outbound

This paper cites Dial one for scam: A large-scale analysis of technical support scams.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Dial one for scam: A large-scale analysis of technical support scams

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.068423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f524fa72-2f51-47c5-ba3b-bd6094da5982 · outbound

This paper cites Mobile tactics.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Mobile tactics

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.070733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc3821ed-ec6a-4d86-838c-d7ebe0b06b50 · outbound

This paper cites On sms phishing tactics and infrastructure.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels On sms phishing tactics and infrastructure

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.072635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 530c5378-d131-41e9-a941-d5d00217dbf9 · outbound

This paper cites Ignore Previous Prompt: Attack Techniques For Language Models.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Ignore Previous Prompt: Attack Techniques For Language Models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.074424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76ec4a41-819f-4c03-b9b3-8a24fa14a0d2 · outbound

This paper cites Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.076927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53c99c5b-a7fa-4781-bdc5-065f59d8fb16 · outbound

This paper cites Are these ads safe: Detecting hidden attacks through the mobile app-web interfaces.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Are these ads safe: Detecting hidden attacks through the mobile app-web interfaces

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.078981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4168044c-5d3c-41e6-8a3a-d1845437f86e · outbound

This paper cites AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.080767Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fd5e405-8914-4acb-833a-e3bdedb018bb · outbound

This paper cites Ba- belview: Evaluating the impact of code injection attacks in mobile webviews.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Ba- belview: Evaluating the impact of code injection attacks in mobile webviews

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.083186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc5f364a-254c-4acd-b37b-729a53c31945 · outbound

This paper cites Identifying the Risks of LM Agents with an LM-Emulated Sandbox.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Identifying the Risks of LM Agents with an LM-Emulated Sandbox

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.085299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75215638-5e13-4422-9efb-69520a1a0b52 · outbound

This paper cites Understanding in-app ads and detecting hidden attacks through the mobile app-web interface.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Understanding in-app ads and detecting hidden attacks through the mobile app-web interface

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.087636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b70b3c18-cd7f-44a7-ab6b-3e132ac482f7 · outbound

This paper cites do anything now.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels do anything now

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.089785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d8ce6a7-300b-481b-b0b0-fbb4e6f12f1e · outbound

This paper cites What mo- bile ads know about mobile users.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels What mo- bile ads know about mobile users

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.091710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fcdb333-3133-4be5-a0ae-beb878d463ec · outbound

This paper cites Scan- droid: Automated side-channel analysis of android apis.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Scan- droid: Automated side-channel analysis of android apis

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.093680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e2df3cf-134e-47b9-8a64-ee0b3883b322 · outbound

This paper cites Autoeval: A practical framework for autonomous evaluation of mobile agents.arXiv preprint arXiv:2503.02403, 2025.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Autoeval: A practical framework for autonomous evaluation of mobile agents.arXiv preprint arXiv:2503.02403, 2025

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.095626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e12a5b2-1f8b-4ba3-ae80-550cdf80c428 · outbound

This paper cites Understanding and detecting mobile ad fraud through the lens of invalid traf- fic.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Understanding and detecting mobile ad fraud through the lens of invalid traf- fic

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.097448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5c21188-30a4-44cb-924c-ac616e75638b · outbound

This paper cites Data breaches, phishing, or malware? understanding the risks of stolen credentials.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Data breaches, phishing, or malware? understanding the risks of stolen credentials

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.099808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4870b70-7b04-4b7e-af3a-a73c18c5b763 · outbound

This paper cites Understanding influences on SMS phishing de- tection: User behavior, demographics, and message attributes.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Understanding influences on SMS phishing de- tection: User behavior, demographics, and message attributes

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.101896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96ff0790-60ff-4665-9633-7e7b669fbf03 · outbound

This paper cites SafeArena: Evaluating the Safety of Autonomous Web Agents.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels SafeArena: Evaluating the Safety of Autonomous Web Agents

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.104345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08d8ff27-a72c-4464-bad1-8c30bc57d3fb · outbound

This paper cites Vladika, A.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Vladika, A

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.106510Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a67007b-9e3f-46c9-a6f3-25d611243972 · outbound

This paper cites The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.108715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 893ea7e0-223a-4eb8-88ae-7e2c013efb31 · outbound

This paper cites Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.110838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef74d904-99af-4f85-aee3-56bbc3fe0d1f · outbound

This paper cites MobileAgentBench: An Efficient and User-Friendly Benchmark for Mobile LLM Agents.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels MobileAgentBench: An Efficient and User-Friendly Benchmark for Mobile LLM Agents

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.113238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f25db0f-8281-408f-8b19-34c60911675a · outbound

This paper cites Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.116080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13b1dfed-95de-4903-ba57-8e0ab1e377c5 · outbound

This paper cites The danger of minimum exposures: Understanding cross-app information leaks on ios through multi-side-channel learning.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels The danger of minimum exposures: Understanding cross-app information leaks on ios through multi-side-channel learning

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.118434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5187e3f8-ddbc-49ef-b93f-23f7013e2313 · outbound

This paper cites Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.120540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7c52400-5df9-4352-bfc8-0d86194a92cd · outbound

This paper cites Autodroid: Llm-powered task automation in android.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Autodroid: Llm-powered task automation in android

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.123202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 077d67eb-3cee-4220-9fe0-249b7cb1504e · outbound

This paper cites DroidBot-GPT: GPT-powered UI Automation for Android.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels DroidBot-GPT: GPT-powered UI Automation for Android

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.125358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 848eac8b-7613-413b-bd90-4e51f175d1f7 · outbound

This paper cites Dissecting Adversarial Robustness of Multimodal LM Agents.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Dissecting Adversarial Robustness of Multimodal LM Agents

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.127507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42f0340d-d8d1-404f-971d-136ec7b942af · outbound

This paper cites From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.129664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be2008a9-e718-4f92-ac24-039d8f74acc3 · outbound

This paper cites GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.131932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd05fd27-4f0e-4221-84b0-9de671b3f133 · outbound

This paper cites Under- standing and detecting overlay-based android malware at mar- ket scales.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Under- standing and detecting overlay-based android malware at mar- ket scales

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.134335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6594acf-0b67-49e7-b3e5-98d8357b23cd · outbound

This paper cites {Iframes/Popups} are dangerous in mobile {WebView}: Studying and mitigating differential context vulnerabilities.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels {Iframes/Popups} are dangerous in mobile {WebView}: Studying and mitigating differential context vulnerabilities

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.136404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 685663bc-a762-4cc2-a462-ddb1c8deee68 · outbound

This paper cites In-Context Defense in Computer Agents: An Empirical Study.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels In-Context Defense in Computer Agents: An Empirical Study

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.138263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00ece843-2841-4e4c-920f-741b93f918b6 · outbound

This paper cites Benchmarking and defend- ing against indirect prompt injection attacks on large language models.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Benchmarking and defend- ing against indirect prompt injection attacks on large language models

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.140603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca5295f3-4cd3-4494-800b-26547420341e · outbound

This paper cites Yuan, L.A.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Yuan, L.A

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.142649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f281932-5d65-49e8-8d7a-b745b7c28f33 · outbound

This paper cites R-Judge: Benchmarking Safety Risk Awareness for LLM Agents.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels R-Judge: Benchmarking Safety Risk Awareness for LLM Agents

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.144746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9b566a5-ee7c-4e37-92ae-3a58e6dc53d0 · outbound

This paper cites Leveraging LLMs and attention-mechanism for automatic annotation of historical maps.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Leveraging LLMs and attention-mechanism for automatic annotation of historical maps

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.146945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a58d006-8bdf-4b43-8c99-d0ca4e8ce987 · outbound

This paper cites The dark alleys of madison avenue: Understanding malicious adver- tisements.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels The dark alleys of madison avenue: Understanding malicious adver- tisements

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.149378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83d778b0-5208-4d57-920a-5873b4caff8b · outbound

This paper cites Research on third-party libraries in android apps: A taxonomy and systematic literature review.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Research on third-party libraries in android apps: A taxonomy and systematic literature review

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.151478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d7ec842-253c-4e49-b352-c27462e692b5 · outbound

This paper cites Appagent: Multimodal agents as smartphone users.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Appagent: Multimodal agents as smartphone users

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.153403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a86d7c8c-49a7-4c9f-af6d-dbf61872b44a · outbound

This paper cites Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.155316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78b7bcd3-b282-4374-9897-debc9b60c4f8 · outbound

This paper cites Identity confusion in {WebView-based} mobile app- in-app ecosystems.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Identity confusion in {WebView-based} mobile app- in-app ecosystems

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.157447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b93f3110-dcd8-4a69-b6f1-c34dd5be42c6 · outbound

This paper cites Attacking Vision-Language Computer Agents via Pop-ups.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Attacking Vision-Language Computer Agents via Pop-ups

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.159564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96a7df1a-d014-448a-80d2-bccedc3905e9 · outbound

This paper cites Gpt-4v(ision) is a generalist web agent, if grounded.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Gpt-4v(ision) is a generalist web agent, if grounded

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.161591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87524caa-95f4-4643-bee0-1bfaf953c421 · outbound

This paper cites Moba: A two-level agent system for efficient mobile task automation.CoRR, abs/2410.13757, 2024.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Moba: A two-level agent system for efficient mobile task automation.CoRR, abs/2410.13757, 2024

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.163433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6210567d-69dd-4eab-8f75-5da1556b6cbd · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.165220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers