The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails | Paper Citation Record

Observation 3629e27b-7410-4117-a788-f0342e2261d7 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.208509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 293a4c02-1cd1-473b-8c3d-18967550e9d9 · outbound

This paper cites Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.213214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19d30d57-97eb-4213-8a8e-dd7390c0d1ce · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.217428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20731d07-f05d-41c5-8049-214322b452be · outbound

This paper cites On Evaluating Adversarial Robustness.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails On Evaluating Adversarial Robustness

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.222098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65ba52db-99ea-49f5-9a26-08cf1fa175f0 · outbound

This paper cites Choquette-Choo, Matthew Jagielski, Irena Gao, Anas Awadalla, Pang Wei Koh, Daphne Ippolito, Katherine Lee, Florian Tramer, and Ludwig Schmidt.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Choquette-Choo, Matthew Jagielski, Irena Gao, Anas Awadalla, Pang Wei Koh, Daphne Ippolito, Katherine Lee, Florian Tramer, and Ludwig Schmidt

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:20:23.650888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9d268cf6-097e-4be5-8792-55265e7496e5 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.639106Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2349667f-29de-4e3e-8a97-378435d08351 · outbound

This paper cites MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.233147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dafb9fc7-9281-4118-bae0-38fd2973383a · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.627678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 27324d3e-51bd-489e-8c99-24bf9002c4bf · outbound

This paper cites Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.240423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2b19fb0-28bc-41c9-96b4-5a6df5bbf9a5 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.616878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation aa0637ab-e2eb-49f2-bf88-d3e686b00ece · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 11

Resolution: metadata mismatch; raw_fallback, observed 2026-08-06T00:20:23.105207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2e619a46-978c-4d59-9b1d-11627e5c27c7 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.606201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation edc76c58-25e7-4372-af92-b6d0ffa6960f · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.255497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe28d7eb-ba5a-4898-a8e6-23ea15849ddf · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.589203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4119471f-1454-40f2-a60b-7e69d8a05a92 · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.262884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d06838b-2f9c-4f70-861c-be723031ea80 · outbound

This paper cites On the Efficacy of Adversarial Data Collection for Question Answering: Results from a Large-Scale Randomized Study.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails On the Efficacy of Adversarial Data Collection for Question Answering: Results from a Large-Scale Randomized Study

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.267252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7800fa2b-6e04-4735-8d82-29b0693692e0 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.271722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c0ac5b2-486e-47ea-b6d8-8f49d5df4741 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.575516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b61a8b09-2de5-4650-bc09-4ffaac5b1fb0 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.279092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f02b9109-8cbf-4441-b4f2-5d0fc0f61707 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.283575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec82f193-a6aa-4250-8bb7-2d180c2146e7 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.287942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8760fbd3-bc4e-40e2-8d3f-3cc86fb4f6ed · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.291089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1614d059-5638-498a-8278-cf6fbd934fa6 · outbound

This paper cites VLM-Guard: Safeguarding Vision-Language Models via Fulfilling Safety Alignment Gap.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails VLM-Guard: Safeguarding Vision-Language Models via Fulfilling Safety Alignment Gap

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.298804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f8001ca-87d6-4fa8-96f7-165e392fcac5 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.302312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b42fbd40-a4ce-45eb-8d37-0dc27fa02cd5 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.545105Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8741ea4c-386f-4717-bb26-ba1589397243 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.533578Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1a24d622-95ef-403a-993e-a131ef0ca629 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.311719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1780050e-1813-4672-9553-8d4fe8b2b2db · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.314629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7822d158-b88b-4c1d-8e58-6a6561094e08 · outbound

This paper cites Refusing Safe Prompts for Multi-modal Large Language Models.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Refusing Safe Prompts for Multi-modal Large Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.318597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba9c76ed-5b6a-449e-a75b-96edd893f93d · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.515217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 799f4308-acdd-42a5-806b-32bc32e5d259 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.325954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58c1b2bf-2f9f-4780-bd39-e3a18448dc6a · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 32

Resolution: malformed identifier; raw_fallback, observed 2026-08-06T00:20:23.496141Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a578fb14-5c7e-45a0-b063-8f9b1e04ba24 · outbound

This paper cites ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.332257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f3881ea-9d8f-4aa3-bc8c-850d1522180d · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.484526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1aef1d6a-b399-4f8e-8ca3-73b5428735ae · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.471139Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ff18ca00-4f44-4e97-b466-aa05c69b0d1d · outbound

This paper cites Ethical and social risks of harm from Language Models.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Ethical and social risks of harm from Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.342928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4af54e52-f4d5-42ef-b8d8-e15434ffb409 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.460866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1f363f9d-f29e-48d6-859e-cdce5c97ffa0 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.349544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a30d7ce3-ca1f-48d7-b8a8-fc755aefc2a9 · outbound

This paper cites "I See What You Did There": Can Large Vision-Language Models Understand Multimodal Puns?.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails "I See What You Did There": Can Large Vision-Language Models Understand Multimodal Puns?

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.352986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 261510be-0e30-48ff-ac70-99efa09e7438 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.442203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 36128199-eab8-4d82-94f2-98beb01da3ad · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.430820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7da049e2-d57d-4f9a-818b-08ca78ef07da · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.418421Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation abf8fbce-344f-4e75-b73b-1bfb05cf20a1 · outbound

This paper cites Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-08-06T00:20:22.571078Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 750311c0-82a3-445d-99be-3b4c1f8c7ad9 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.370171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b10d4a3-fc03-4c20-98aa-86817400bdc3 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 45

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.407913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5b0a9b86-daee-4e2e-8222-7f02d7b7951c · outbound

This paper cites AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.377020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c10b5a7b-71bf-407d-b579-2ce67816bc10 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 47

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.396313Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 29f86938-8561-4a13-b4f7-26c35929d71c · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.384085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93dfcea6-fce9-4c60-a72f-fdb0c5b819ec · outbound

This paper cites LLM Safeguard is a Double-Edged Sword: Exploiting False Positives for Denial-of-Service Attacks.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails LLM Safeguard is a Double-Edged Sword: Exploiting False Positives for Denial-of-Service Attacks

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.387882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d68626e0-fae3-4cee-90fd-af65acdd7ef6 · outbound

This paper cites Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.392337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bc85b1a-3960-4f20-bac0-ddfd98d4493f · outbound

This paper cites MM-RLHF: The Next Step Forward in Multimodal LLM Alignment.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails MM-RLHF: The Next Step Forward in Multimodal LLM Alignment

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.395848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8600155c-99c9-4577-8d15-a739beab43f4 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 52

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.377311Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fc32c107-a355-48c9-945c-fdf0ba806a2c · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.402818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52e279bf-dc64-4ebc-93b3-709a683137da · outbound

This paper cites CollabEdit: Towards Non-destructive Collaborative Knowledge Editing.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails CollabEdit: Towards Non-destructive Collaborative Knowledge Editing

Reference 54

Resolution: verified exact; local_arxiv, observed 2026-08-06T00:20:22.516822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 62ecbeb2-692a-4903-97fc-38e54eb952d6 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 56

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.359858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9bc6775c-2ebd-4ae6-b22d-053be37a69f1 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.413436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11411603-f865-4747-ad19-d8b76f12c340 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 58

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.342786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f363cc9c-51f0-499c-bebf-e3a7a083062b · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 59

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.333295Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a2ce028c-2d0a-4064-9c56-f361e8fdecce · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 60

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.320952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6e029c92-676c-4b85-ab24-26f683f3759e · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 61

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.309685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 574d97e9-d687-4042-ad06-ec0401bbd868 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 62

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.298534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4e9b26bb-741d-4322-bffc-3a47e72b1c53 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 63

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.285618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f9f8ed3a-a676-4d4e-824f-8ab7f59162c6 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 64

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.274609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a2d1ead0-027d-4083-a12d-9a8d9b5519e0 · outbound

This paper cites C.2 Realistic User Simulation Prompts for ASR r Realistic prompts simulate authentic user requests tailored to each specific image.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails C.2 Realistic User Simulation Prompts for ASR r Realistic prompts simulate authentic user requests tailored to each specific image

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:20:23.261894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c560f9d8-1eb9-4197-8cdc-c10ad962623b · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 66

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.250046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2f1a88e6-7a6c-45ad-b8f7-231aebcce5d5 · outbound

This paper cites remove the background,.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails remove the background,

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:20:23.238511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 159e6f6e-5c4e-4367-8110-ff38c6506e58 · outbound

This paper cites write a story about this,.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails write a story about this,

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:20:23.225904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fd08f194-13f4-49e1-b0a9-3dc95a565409 · outbound

This paper cites Requirements:.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Requirements:

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:20:23.210792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8841b289-ffc1-4213-a51b-f67bdefbf48b · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 70

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.199732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d2cff1bf-d7b1-4947-a6ac-388156a4ca26 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 71

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.187414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b9bf7605-e520-43c6-94f7-412aca7657e0 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 72

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:20:23.175817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2f5279ce-6a61-44ff-a213-f1dee17996ed · outbound

This paper cites Output format: Request 1: [Your first user prompt here] Request 2: [Your second user prompt here] Request 3: [Your third user prompt here].

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Output format: Request 1: [Your first user prompt here] Request 2: [Your second user prompt here] Request 3: [Your third user prompt here]

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:20:23.164452Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c08cae40-6e14-474c-8c67-1d30353fa4b6 · outbound

This paper cites an unresolved cited work.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Unresolved cited work

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.295055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers