Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-18T08:14:51.102085Z
Paper Citation Record · LEDGER
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents
As of 29 July 2026, this Paper Citation Record lists 69 of 69 outbound references and 3 inbound Pith citation observations for arXiv:2510.10073.
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 2026-07-28T06:31:03.373048+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-07-01T01:55:40.954429Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-07-10T12:15:01.137692Z
Reference resolution
69 of 69 outbound references displayed
- verified exact36
- verified fuzzy31
- unresolved0
- parse uncertain0
- malformed identifier0
- metadata mismatch2
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation e0a18e55-c0c5-40f1-8ad1-ae993bb191db · outbound
This paper cites Agent-E: From Autonomous Web Navigation to Foundational Design Principles in Agentic Systems.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Agent-E: From Autonomous Web Navigation to Foundational Design Principles in Agentic Systems
Reference 1
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T08:16:06.511644Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation f0eb1c1c-6867-4888-9daf-9eefbaece77d · outbound
This paper cites 2025.Introducing Claude 3.7 Sonnet and Claude Code.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents 2025.Introducing Claude 3.7 Sonnet and Claude Code
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.284178Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation c0d4989b-fb17-44ed-b6c6-9b24cd2bc0a5 · outbound
This paper cites 2025.Introducing Claude 4.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents 2025.Introducing Claude 4
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.287460Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 22155528-09e8-4365-9900-ab2d57b02b0b · outbound
This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Reference 4
- Resolution
- verified exact
- local_arxiv, observed 2026-05-18T08:16:06.547723Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 7194835e-ddc1-4c81-972a-1c5ac25fbad4 · outbound
This paper cites an unresolved cited work.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unresolved cited work
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.306553Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 4646a28e-20d2-4764-92ef-1bfcc5f2a65c · outbound
This paper cites Multilingual Jailbreak Challenges in Large Language Models.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Multilingual Jailbreak Challenges in Large Language Models
Reference 6
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T08:16:06.485283Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 51e16ce5-49cb-4a34-bcd9-45e57c6c16d8 · outbound
This paper cites A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily
Reference 7
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T08:16:06.618493Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 4865609d-72a9-4f23-b11c-1c7318917a19 · outbound
This paper cites WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks
Reference 8
- Resolution
- verified exact
- local_arxiv, observed 2026-05-18T08:16:06.607812Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 1133bec4-a68b-4e08-8d90-44b00ab32d60 · outbound
This paper cites an unresolved cited work.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unresolved cited work
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.300150Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 689c9b53-07b1-46a8-86ee-fc8666004e6a · outbound
This paper cites an unresolved cited work.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unresolved cited work
Reference 10
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.274028Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation c6b6c83a-6dca-4ec9-aed3-b060ce150775 · outbound
This paper cites Seed1.5-VL Technical Report.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Seed1.5-VL Technical Report
Reference 11
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T08:16:06.590003Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation efc38285-8b7b-4371-9a42-50de42b92105 · outbound
This paper cites an unresolved cited work.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unresolved cited work
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.293604Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 8db74e54-ae78-411b-b2f7-268c27215ade · outbound
This paper cites GPT-4o System Card.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents GPT-4o System Card
Reference 13
- Resolution
- verified exact
- local_arxiv, observed 2026-05-18T08:16:06.633768Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 293498f0-6418-43ad-baff-096ca6d23ba5 · outbound
This paper cites Manipulating LLM Web Agents with Indirect Prompt Injection Attack via HTML Accessibility Tree.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Manipulating LLM Web Agents with Indirect Prompt Injection Attack via HTML Accessibility Tree
Reference 14
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T08:16:06.436235Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 7ba88fdd-6681-42e8-8355-094cda343b08 · outbound
This paper cites an unresolved cited work.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unresolved cited work
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.363477Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation f1d339fc-9115-4c24-90e9-1c8225e2607a · outbound
This paper cites VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks
Reference 16
- Resolution
- verified exact
- local_arxiv, observed 2026-05-18T08:16:06.428195Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 9d841a2f-ec22-4551-9981-9270bd8ee601 · outbound
This paper cites Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents
Reference 17
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T08:16:06.580695Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 4d784290-14fd-4719-a7b1-7b1770878510 · outbound
This paper cites an unresolved cited work.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unresolved cited work
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.281052Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 31b9ee17-154a-4d3d-9c42-031cac7de460 · outbound
This paper cites an unresolved cited work.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unresolved cited work
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.290461Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 0fecf15d-8913-408e-b9b8-42f11205622c · outbound
This paper cites ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents
Reference 20
- Resolution
- verified exact
- arxiv_id, observed 2026-06-05T02:16:16.756993Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 4c5910c0-1d17-4c3c-8183-535f17c4a899 · outbound
This paper cites an unresolved cited work.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unresolved cited work
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.277608Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation b0a9e03e-7dde-4219-b5d8-0fb026d40871 · outbound
This paper cites DeepInception: Hypnotize Large Language Model to Be Jailbreaker.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents DeepInception: Hypnotize Large Language Model to Be Jailbreaker
Reference 22
- Resolution
- verified exact
- arxiv_id, observed 2026-05-19T10:37:07.279605Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 61c06b51-de62-4510-bc75-27c1f4eb8973 · outbound
This paper cites an unresolved cited work.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unresolved cited work
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.359759Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 3aed6e1d-33d3-427c-919a-4c50a752f088 · outbound
This paper cites an unresolved cited work.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unresolved cited work
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.352835Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation fa83084f-1b4c-4a0a-89ca-c0d655fb32e1 · outbound
This paper cites an unresolved cited work.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unresolved cited work
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.370706Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 0840a47b-79d2-49ce-af44-83ddcce8d49c · outbound
This paper cites an unresolved cited work.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unresolved cited work
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.367608Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation a50163c8-9355-496d-8880-5f96ee336835 · outbound
This paper cites an unresolved cited work.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unresolved cited work
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.349637Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 1147cac4-f258-464b-b644-e0fe74845168 · outbound
This paper cites Agentsafe: Benchmarking the safety of embodied agents on hazardous instructions.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Agentsafe: Benchmarking the safety of embodied agents on hazardous instructions
Reference 28
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T08:16:06.467765Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation ebfa97b2-0fd0-48b7-9744-28a2cde8783e · outbound
This paper cites an unresolved cited work.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unresolved cited work
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.356392Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation f14962bb-d1b9-426c-855d-573156118ba3 · outbound
This paper cites Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks?.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks?
Reference 30
- Resolution
- verified exact
- arxiv_id, observed 2026-05-28T02:04:09.776894Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation acb3bcfb-07be-437c-9c28-153f74fe47a2 · outbound
This paper cites an unresolved cited work.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unresolved cited work
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.339301Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation b642d20a-70ac-4fbf-9bc4-51384f5ce6ae · outbound
This paper cites 2025.GPT-5 is here.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents 2025.GPT-5 is here
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.373983Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation bbec563b-9567-4cca-b188-2706b71e28f2 · outbound
This paper cites UI-TARS: Pioneering Automated GUI Interaction with Native Agents.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents UI-TARS: Pioneering Automated GUI Interaction with Native Agents
Reference 33
- Resolution
- verified exact
- local_arxiv, observed 2026-05-18T08:16:06.461087Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 43d77cab-d2a2-47a0-a41c-ad07b46c5cbc · outbound
This paper cites Evaluating Cultural and Social Awareness of LLM Web Agents.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Evaluating Cultural and Social Awareness of LLM Web Agents
Reference 34
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T08:16:06.563526Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation b646e8c9-9e20-431d-8e89-c81daf40661e · outbound
This paper cites POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models
Reference 35
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T08:16:06.638234Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 8cbc40e9-8650-4df5-90f7-ff60020b620f · outbound
This paper cites an unresolved cited work.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unresolved cited work
Reference 36
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.346386Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 7a8a1491-5425-48c8-a5e5-55990f165ecd · outbound
This paper cites Gemini: A Family of Highly Capable Multimodal Models.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Gemini: A Family of Highly Capable Multimodal Models
Reference 37
- Resolution
- verified exact
- local_arxiv, observed 2026-05-18T08:16:06.568915Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 0800ca9b-3731-44a1-b6c0-1a44082198da · outbound
This paper cites GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
Reference 38
- Resolution
- verified exact
- local_arxiv, observed 2026-05-18T08:16:06.474138Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation afcc938e-df52-434b-83da-44437f126749 · outbound
This paper cites SafeArena: Evaluating the Safety of Autonomous Web Agents.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents SafeArena: Evaluating the Safety of Autonomous Web Agents
Reference 39
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T08:16:06.629152Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation bf469bc2-a70c-4199-a2ae-9f541b9cd4d9 · outbound
This paper cites AdInject: Real-World Black-Box Attacks on Web Agents via Advertising Delivery.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents AdInject: Real-World Black-Box Attacks on Web Agents via Advertising Delivery
Reference 40
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T08:16:06.533091Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 17fd2714-c315-4cf1-b6a5-a2de4ea56449 · outbound
This paper cites Manipulating Multimodal Agents via Cross-Modal Prompt Injection.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Manipulating Multimodal Agents via Cross-Modal Prompt Injection
Reference 41
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T08:16:06.490295Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation fc53c0fb-c57a-499e-a02c-2be32b1a5149 · outbound
This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
Reference 42
- Resolution
- verified exact
- local_arxiv, observed 2026-05-18T08:16:06.575129Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 7f31ea17-97b5-46a3-86b8-eee35d902fb8 · outbound
This paper cites an unresolved cited work.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unresolved cited work
Reference 43
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.313419Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 0ece1b67-d30a-4906-a6f8-fcb3a432c2ce · outbound
This paper cites an unresolved cited work.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unresolved cited work
Reference 44
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.335561Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 8ba4c7c6-d9bd-4502-b2e3-caa586b372fb · outbound
This paper cites an unresolved cited work.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unresolved cited work
Reference 45
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.303108Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 76c9c2b3-d6d6-425f-a9a7-cdf537463053 · outbound
This paper cites an unresolved cited work.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unresolved cited work
Reference 46
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.316469Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 59538643-4347-445c-9aba-a0851a2bca8d · outbound
This paper cites arXiv preprint arXiv:2510.01243 , year=.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents arXiv preprint arXiv:2510.01243 , year=
Reference 47
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T08:16:06.517112Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 014e0a19-ae6e-4753-9adb-3a49d8d266be · outbound
This paper cites an unresolved cited work.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unresolved cited work
Reference 48
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.331836Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 29352bce-5c4e-498c-9204-1a9abca2322d · outbound
This paper cites an unresolved cited work.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unresolved cited work
Reference 49
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.296837Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation d8178ba8-b2e4-415a-af44-78e1a18d469e · outbound
This paper cites an unresolved cited work.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unresolved cited work
Reference 50
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.342958Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation be7f25e2-e031-4af3-a856-cf9d225e1f76 · outbound
This paper cites Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction
Reference 51
- Resolution
- verified exact
- local_arxiv, observed 2026-05-18T08:16:06.527370Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 40a3bbed-8b25-4532-9396-794ccddd8066 · outbound
This paper cites an unresolved cited work.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unresolved cited work
Reference 52
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.328219Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation bef5bc81-cb43-4fd3-959a-cd83f43683fc · outbound
This paper cites Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
Reference 53
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T08:16:06.454998Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation b0c64546-9864-46f5-b189-20dedfddc296 · outbound
This paper cites an unresolved cited work.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unresolved cited work
Reference 54
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.377288Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation a715de99-dcb7-4650-b1d3-304988d2e1c3 · outbound
This paper cites SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models
Reference 55
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T08:16:06.542069Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 5e648ac5-8fc9-427f-8d54-fc82f990cf13 · outbound
This paper cites Unveiling the Safety of GPT-4o: An Empirical Study using Jailbreak Attacks.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unveiling the Safety of GPT-4o: An Empirical Study using Jailbreak Attacks
Reference 56
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T08:16:06.495604Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 94db8459-1487-4ca1-a188-659b4b450c59 · outbound
This paper cites an unresolved cited work.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unresolved cited work
Reference 57
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.310100Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 5db08660-b4bb-4fc9-ac48-6ec409bfe460 · outbound
This paper cites Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025
Reference 58
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T08:16:06.521830Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 0ae7e906-c352-40a3-8435-e4336dc3f1f2 · outbound
This paper cites Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models
Reference 59
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T08:16:06.448868Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation c3772ce9-a11c-4602-969f-2c4648a84159 · outbound
This paper cites Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findings.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findings
Reference 60
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T08:16:06.596203Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 15bcc2ec-6a2a-489a-8f87-3d5517cd4031 · outbound
This paper cites PROMPTFUZZ: Harnessing Fuzzing Techniques for Robust Testing of Prompt Injection in LLMs.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents PROMPTFUZZ: Harnessing Fuzzing Techniques for Robust Testing of Prompt Injection in LLMs
Reference 61
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T08:16:06.642846Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation c59c361b-10ba-4e26-8941-72637653d8ee · outbound
This paper cites GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher
Reference 62
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T08:16:06.624171Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 1d11b200-8d8d-4366-bd12-dc6de861d631 · outbound
This paper cites GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
Reference 63
- Resolution
- verified exact
- local_arxiv, observed 2026-05-18T08:16:06.442597Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 4c70b9c4-7d0e-4ad5-9835-fb595dc778fb · outbound
This paper cites an unresolved cited work.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Unresolved cited work
Reference 64
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.323971Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 4940c25b-6c10-484d-b6dc-cb339f63a28b · outbound
This paper cites InProceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents InProceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Reference 65
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T08:16:07.320027Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 5dacde04-0c77-4eb8-926a-8fb450e972c5 · outbound
This paper cites Attacking Vision-Language Computer Agents via Pop-ups.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Attacking Vision-Language Computer Agents via Pop-ups
Reference 66
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T08:16:06.585253Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation c93aed80-7fb8-4342-a16d-6f9f36f266ca · outbound
This paper cites WebArena: A Realistic Web Environment for Building Autonomous Agents.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents WebArena: A Realistic Web Environment for Building Autonomous Agents
Reference 67
- Resolution
- verified exact
- local_arxiv, observed 2026-05-18T08:16:06.500670Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 9de241ee-70ca-4aa3-bdfd-52619877cbd7 · outbound
This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Universal and Transferable Adversarial Attacks on Aligned Language Models
Reference 68
- Resolution
- verified exact
- local_arxiv, observed 2026-05-18T08:16:06.612720Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 00769ba5-9cde-4e9e-8f28-bdb73b424cbb · outbound
This paper cites PRISM: Programmatic Reasoning with Image Sequence Manipulation for LVLM Jailbreaking.
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents PRISM: Programmatic Reasoning with Image Sequence Manipulation for LVLM Jailbreaking
Reference 69
- Resolution
- verified exact
- local_arxiv, observed 2026-05-18T08:16:06.505883Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Pith citing papers
Observation 31c63b8b-5014-49e4-82e1-11de251a9e98 · inbound
Governance by Construction for Generalist Agents cites this paper.
Governance by Construction for Generalist Agents SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents
Reference 27
- Resolution
- verified exact
- local_arxiv, observed 2026-05-21T04:53:58.035574Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 6ac96e90-76a3-4bc6-8efa-e35c19c67673 · inbound
Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation cites this paper.
Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents
Reference 229
- Resolution
- verified exact
- local_arxiv, observed 2026-06-27T13:20:56.776294Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.
Observation 6d8fb2c5-780e-4420-8260-0c41ba7fd405 · inbound
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens cites this paper.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents
Reference 36
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T12:35:44.111703Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.