Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-15T20:28:15.736267Z
Paper Citation Record · LEDGER
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents
As of 20 August 2026, this Paper Citation Record lists 71 of 71 outbound references and 3 inbound Pith citation observations for arXiv:2505.12981.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-06T21:11:18.279076Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-08-06T21:11:18.938391Z
Reference resolution
71 of 71 outbound references displayed
- verified exact1
- verified fuzzy33
- unresolved37
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 99b7a93a-7272-4a2e-9ea1-969085f8c947 · outbound
This paper cites Large language models for software engi- neering: A systematic literature review,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Large language models for software engi- neering: A systematic literature review,
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.460315Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fb9c7e46-4068-42fd-b65d-fe4a9a0eaa72 · outbound
This paper cites GUI Agents with Foundation Models: A Comprehensive Survey.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents GUI Agents with Foundation Models: A Comprehensive Survey
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.465072Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation feb75a19-f460-4597-9a9c-659c372cd1d9 · outbound
This paper cites Large Language Model-Brained GUI Agents: A Survey.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Large Language Model-Brained GUI Agents: A Survey
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.470688Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 46808128-85dc-4ea0-832b-3107793b01db · outbound
This paper cites Foundations and Recent Trends in Multimodal Mobile Agents: A Survey.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Foundations and Recent Trends in Multimodal Mobile Agents: A Survey
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.475515Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 96f9acc5-bf67-4785-9d9e-848cf517c4da · outbound
This paper cites Ai agents vs. ai assistants,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Ai agents vs. ai assistants,
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.600419Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 575bc650-19bb-4617-9483-67f52daead4c · outbound
This paper cites Agentic ai is revolutionizing business and daily life,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Agentic ai is revolutionizing business and daily life,
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.586843Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 4121a780-373e-4bcc-81c5-51c4defbe12a · outbound
This paper cites 6 ai trends you’ll see more of in 2025,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents 6 ai trends you’ll see more of in 2025,
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.574946Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation e2a61153-73e8-419a-9e4e-4dbd030840b5 · outbound
This paper cites MagicOS,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents MagicOS,
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.564154Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 69d8fc46-dd78-40bb-b4f1-47c95352ec12 · outbound
This paper cites AutoGLM: Autonomous Foundation Agents for GUIs.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents AutoGLM: Autonomous Foundation Agents for GUIs
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.497748Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 46d22e66-63e7-4913-bc19-cd7c3de371c0 · outbound
This paper cites This android skin has an ai that can order coffee and manage subscriptions,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents This android skin has an ai that can order coffee and manage subscriptions,
Reference 10
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.552201Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 19bc6f2e-168c-4d3f-a3cd-f1076f75a935 · outbound
This paper cites What is an ai agent?.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents What is an ai agent?
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.536252Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 90c3a263-49f4-40b1-b414-616d1062a774 · outbound
This paper cites Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.510735Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d8de09b3-c378-41ce-8c42-f8db2d215efc · outbound
This paper cites When LLMs Go Online: The Emerging Threat of Web-Enabled LLMs.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents When LLMs Go Online: The Emerging Threat of Web-Enabled LLMs
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.514564Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c66bc859-a7e5-4123-8bfd-f398043d1fb7 · outbound
This paper cites WIPI: A New Web Threat for LLM-Driven Web Agents.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents WIPI: A New Web Threat for LLM-Driven Web Agents
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.518527Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ab940673-22a3-405a-8801-09b08bd359b6 · outbound
This paper cites Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
Reference 15
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.523978Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation da1b468c-6fd0-4616-9d8b-231c1a97d3a3 · outbound
This paper cites EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.528843Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 494eb1e6-f899-4489-bfc5-f15213e909f3 · outbound
This paper cites AdvAgent: Controllable Blackbox Red-teaming on Web Agents.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents AdvAgent: Controllable Blackbox Red-teaming on Web Agents
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.532767Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d5d8ae3c-194d-47ce-8053-495b49c60c3f · outbound
This paper cites Towards Action Hijacking of Large Language Model-based Agent.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Towards Action Hijacking of Large Language Model-based Agent
Reference 18
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.536913Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9f10c6c6-bf12-4df6-b692-6afbe08173e4 · outbound
This paper cites Translating Natural Language to Planning Goals with Large-Language Models.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Translating Natural Language to Planning Goals with Large-Language Models
Reference 19
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.541257Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0fa684fa-6d12-4493-b274-52876b7c2d93 · outbound
This paper cites Large language models versus natural language understand- ing and generation,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Large language models versus natural language understand- ing and generation,
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.524220Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 20e42c18-74c7-4068-bc5a-39e0fa51de33 · outbound
This paper cites Droidbot: a lightweight ui-guided test input generator for android,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Droidbot: a lightweight ui-guided test input generator for android,
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.511567Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 02d806ec-d222-4983-a959-b3d293c405ed · outbound
This paper cites an unresolved cited work.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Unresolved cited work
Reference 22
- Resolution
- unresolved
- raw_fallback, observed 2026-08-15T20:28:16.498610Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation b05910a9-f54d-470a-af08-805e9ac62862 · outbound
This paper cites Create your own accessibility service,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Create your own accessibility service,
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.486642Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 9b66fde0-2bba-42bb-870b-08c00424ae1f · outbound
This paper cites OriginOS,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents OriginOS,
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.473491Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 5e409692-1d84-4076-a7b0-9b4718483677 · outbound
This paper cites Android API reference,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Android API reference,
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.461013Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 4f718196-e2c6-4f08-95eb-0ec9a1ea0fe8 · outbound
This paper cites Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception
Reference 26
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.569817Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4a23c9e3-87af-4814-b621-f950a0e0c3fe · outbound
This paper cites Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration
Reference 27
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.574068Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7a201c8b-83b9-4ead-a2fc-098ed3eb7977 · outbound
This paper cites AppAgent: Multimodal Agents as Smartphone Users.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents AppAgent: Multimodal Agents as Smartphone Users
Reference 28
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.578147Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1b669a69-781e-4628-ab56-f0fdb51d27a7 · outbound
This paper cites Autodroid: Llm-powered task automation in android,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Autodroid: Llm-powered task automation in android,
Reference 29
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.582230Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1bc666bd-498c-40eb-8788-ddf72bd69599 · outbound
This paper cites DroidBot-GPT: GPT-powered UI Automation for Android.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents DroidBot-GPT: GPT-powered UI Automation for Android
Reference 30
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.585884Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3f5ffa76-3f9a-434d-84b5-a95f043a6bfa · outbound
This paper cites Grounding dino: Marrying dino with grounded pre-training for open-set object detection,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Grounding dino: Marrying dino with grounded pre-training for open-set object detection,
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.442685Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 09b8ba84-0319-4d86-9eb7-afbefbba0689 · outbound
This paper cites Write automated tests with UI Automator,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Write automated tests with UI Automator,
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.430588Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 274e3c43-4b4f-4be1-9b1d-b6e9cff2fcd1 · outbound
This paper cites Android Debug Bridge (adb) ,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Android Debug Bridge (adb) ,
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.418097Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 3a8033bc-23ee-4921-b5af-eab63372d490 · outbound
This paper cites Optimization-based prompt injection attack to llm-as-a-judge,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Optimization-based prompt injection attack to llm-as-a-judge,
Reference 34
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.600957Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b1f00ae2-781b-4f72-abab-92af79eb4b69 · outbound
This paper cites Formalizing and benchmarking prompt injection attacks and defenses,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Formalizing and benchmarking prompt injection attacks and defenses,
Reference 35
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.604854Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ff7fb288-4790-49d3-b453-fc9db4b7f447 · outbound
This paper cites ” do anything now.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents ” do anything now
Reference 36
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.608465Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 42e77b37-bf50-44f5-8285-3f7ac23c551d · outbound
This paper cites {LLM-Fuzzer}: Scaling assessment of large language model jailbreaks,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents {LLM-Fuzzer}: Scaling assessment of large language model jailbreaks,
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.382495Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation e3a488a9-08e4-4e83-be21-3303c73d6a5e · outbound
This paper cites Don’t listen to me: understanding and exploring jailbreak prompts of large language models,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Don’t listen to me: understanding and exploring jailbreak prompts of large language models,
Reference 38
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.616010Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f3460d6b-5fbb-4bf6-82e9-5ef7a87e7e05 · outbound
This paper cites An {LLM-Assisted}{Easy-to-Trigger} backdoor attack on code completion models: Injecting disguised vulnerabilities against strong detection,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents An {LLM-Assisted}{Easy-to-Trigger} backdoor attack on code completion models: Injecting disguised vulnerabilities against strong detection,
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.365697Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 32a47015-a569-4aa5-b50b-7ec3950d7610 · outbound
This paper cites Instruction backdoor attacks against customized {LLMs},.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Instruction backdoor attacks against customized {LLMs},
Reference 40
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.623317Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation be98797b-fa49-4604-9f72-c75ad89cd367 · outbound
This paper cites Glitch tokens in large language models: Categorization taxonomy and effective detection,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Glitch tokens in large language models: Categorization taxonomy and effective detection,
Reference 41
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.348550Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 40c2c32d-61ab-499e-a9ba-7d420c2898c2 · outbound
This paper cites Glitchprober: Advancing effective detection and mitigation of glitch tokens in large language models,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Glitchprober: Advancing effective detection and mitigation of glitch tokens in large language models,
Reference 42
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.338541Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 62ad4760-e87e-4304-9783-1806d5498815 · outbound
This paper cites Ui obfuscation and its effects on automated ui analysis for android apps,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Ui obfuscation and its effects on automated ui analysis for android apps,
Reference 43
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.328239Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 4227b7ab-826c-4c79-bc27-a8da5b8e146d · outbound
This paper cites Detecting mobile application spoofing attacks by leveraging user visual similarity perception,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Detecting mobile application spoofing attacks by leveraging user visual similarity perception,
Reference 44
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.316358Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation f1c757a8-4830-4704-9c09-b367060994a7 · outbound
This paper cites Android ui deception revisited: Attacks and defenses,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Android ui deception revisited: Attacks and defenses,
Reference 45
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.304337Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 6f5d1b4c-fef7-4b20-92c4-590194f84cd6 · outbound
This paper cites Android ui deception revisited: Attacks and defenses,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Android ui deception revisited: Attacks and defenses,
Reference 46
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.292635Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 725fe291-9228-409d-9280-f058a87c1d73 · outbound
This paper cites Trapped by the ui: The android case,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Trapped by the ui: The android case,
Reference 47
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.276640Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation ffb6febc-83a2-4217-adc1-64c011e5dd59 · outbound
This paper cites Understanding and detecting overlay-based android malware at market scales,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Understanding and detecting overlay-based android malware at market scales,
Reference 48
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.264079Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 0d4b1e30-1493-481a-8e4f-3d411b059650 · outbound
This paper cites Uncovering intent based leak of sensitive data in android framework,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Uncovering intent based leak of sensitive data in android framework,
Reference 49
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.252857Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 03fbb4d0-1d8c-45cd-9b16-25d6630acf90 · outbound
This paper cites Improving android ap- plication security for intent based attacks,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Improving android ap- plication security for intent based attacks,
Reference 50
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.242149Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 394f7f91-bfcd-4f98-9fec-aa98c621edbd · outbound
This paper cites All your app links are belong to us: understanding the threats of instant apps based attacks,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents All your app links are belong to us: understanding the threats of instant apps based attacks,
Reference 51
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.229795Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 5c04e7da-0152-40f4-80e5-96506681d227 · outbound
This paper cites Measuring the insecurity of mobile deep links of android,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Measuring the insecurity of mobile deep links of android,
Reference 52
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.218243Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 053b905b-7910-4dff-aea8-eccced59d0a5 · outbound
This paper cites Born with a silver spoon: On the (in) security of native granted app privileges in custom android roms,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Born with a silver spoon: On the (in) security of native granted app privileges in custom android roms,
Reference 53
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.206509Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 766d1b52-57ae-46b0-ad1b-5068891351a9 · outbound
This paper cites From logging to leakage: A study of privacy leakage in android app logs,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents From logging to leakage: A study of privacy leakage in android app logs,
Reference 54
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.193395Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation ea8b86cd-303f-4ae9-96c5-3ccdbf14cfa4 · outbound
This paper cites A comprehensive study of privacy leakage vulnerability in android app logs,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents A comprehensive study of privacy leakage vulnerability in android app logs,
Reference 55
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.181163Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 6c49d21e-223a-43e7-9924-9dc18488319f · outbound
This paper cites Sycophancy in Large Language Models: Causes and Mitigations.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Sycophancy in Large Language Models: Causes and Mitigations
Reference 56
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.680312Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 374080c3-0f1f-4202-99ed-914d34b55aaa · outbound
This paper cites Simple synthetic data reduces sycophancy in large language models.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Simple synthetic data reduces sycophancy in large language models
Reference 57
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.684426Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 44a931f0-d291-419b-bea9-dc7ccf511792 · outbound
This paper cites Towards Understanding Sycophancy in Language Models.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Towards Understanding Sycophancy in Language Models
Reference 58
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.688950Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8ec1d1ad-cdd9-4628-ba75-0d56b58a67ec · outbound
This paper cites An- droidinthewild: A large-scale dataset for android device control,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents An- droidinthewild: A large-scale dataset for android device control,
Reference 59
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.168305Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 83268e89-bd71-4d98-aa78-ae2c38df0aa5 · outbound
This paper cites Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection
Reference 60
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.696494Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation de76ec75-0626-46b9-8d9c-f8b13b90315e · outbound
This paper cites Learn to Disguise: Avoid Refusal Responses in LLM's Defense via a Multi-agent Attacker-Disguiser Game.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Learn to Disguise: Avoid Refusal Responses in LLM's Defense via a Multi-agent Attacker-Disguiser Game
Reference 61
- Resolution
- verified exact
- local_arxiv, observed 2026-08-15T20:28:15.924686Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 8b086e51-5a8c-4832-b089-acdd56d1a6bb · outbound
This paper cites Role play with large language models,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Role play with large language models,
Reference 62
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.703713Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cdd899c0-d216-4dd2-bbbb-7f4a6cf82d8c · outbound
This paper cites Jailbreak Attacks and Defenses Against Large Language Models: A Survey.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Jailbreak Attacks and Defenses Against Large Language Models: A Survey
Reference 63
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.707065Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 246cf483-2772-4db7-b0d5-a60017ef997d · outbound
This paper cites Visiontasker: Mobile task automation using vision based ui understanding and llm task planning,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Visiontasker: Mobile task automation using vision based ui understanding and llm task planning,
Reference 64
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:28:16.148542Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation f1e1e46b-17b9-47e0-8f4c-92ba90b6df08 · outbound
This paper cites CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation
Reference 65
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.713601Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 69f1c056-8462-48f2-8ede-907a72d98987 · outbound
This paper cites Appagent v2: Advanced agent for flexible mobile interactions,.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Appagent v2: Advanced agent for flexible mobile interactions,
Reference 66
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.717237Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 542e086c-a4d9-41a8-9bc9-e9ed69b80e83 · outbound
This paper cites Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents
Reference 67
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.721141Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0bbe92f2-0629-4b82-bf90-6bc58020dfb7 · outbound
This paper cites MobileAgentBench: An Efficient and User-Friendly Benchmark for Mobile LLM Agents.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents MobileAgentBench: An Efficient and User-Friendly Benchmark for Mobile LLM Agents
Reference 68
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.724673Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 772e8640-5c0a-4d47-b2cd-beeddf026b6b · outbound
This paper cites UFO: A UI-Focused Agent for Windows OS Interaction.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents UFO: A UI-Focused Agent for Windows OS Interaction
Reference 69
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.728331Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 77f1591b-9d68-45c9-8afa-a0589bd56f6b · outbound
This paper cites ScreenAgent: A Vision Language Model-driven Computer Control Agent.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents ScreenAgent: A Vision Language Model-driven Computer Control Agent
Reference 70
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.732395Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0e437ce2-42e0-4020-b1e2-ce6696ae78fa · outbound
This paper cites Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale.
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale
Reference 71
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:28:15.736267Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Pith citing papers
Observation 17cc5d21-b88f-4424-a663-36f7f9b2cd75 · inbound
SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents cites this paper.
SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents
Reference 25
- Resolution
- verified exact
- local_arxiv, observed 2026-08-06T21:11:18.944034Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 42f0340d-d8d1-404f-971d-136ec7b942af · inbound
Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels cites this paper.
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 b390c2b4-9592-438b-8c59-46d23ed4cef4 · inbound
Mind the Gap: Action Rebinding Attacks against Android GUI Agents cites this paper.
Mind the Gap: Action Rebinding Attacks against Android GUI Agents From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents
Reference 43
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T09:55:00.246179Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.