Paper Citation Record · LEDGER

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security

As of 17 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 2 inbound Pith citation observations for arXiv:2507.22037.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2507.22037 v1

Coverage vector

measured 49 of 49 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T12:09:39.861497Z

measured 51 of 51 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-15T19:19:42.748573Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-05-15T19:19:42.862780Z

Reference resolution

49 of 49 outbound references displayed

verified exact1
verified fuzzy1
unresolved47
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b6a387b5-4de7-4514-8abe-043f34d44487 · outbound

This paper cites an unresolved cited work.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-06T12:09:41.153756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6cd493d6-d804-492f-b72c-8cde5d1c5bb4 · outbound

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

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.603513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28ac7225-4694-4905-93bc-b1e5a7832ad6 · outbound

This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.609477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99973d18-38bc-4707-9038-dca444a98dd8 · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.615039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf046c21-fd53-4e9d-b1c2-edb0f1fd98ce · outbound

This paper cites Image Hijacks: Adversarial Images can Control Generative Models at Runtime.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Image Hijacks: Adversarial Images can Control Generative Models at Runtime

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.620116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e7c6c50-a605-4ac2-bc77-bee751af0b9d · outbound

This paper cites an unresolved cited work.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-06T12:09:41.137026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9cb7fc64-0366-4d19-ab69-4a448b819912 · outbound

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

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.630560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d005cb89-ec4f-4219-824f-e9cb83aa415a · outbound

This paper cites Stable Reinforcement Learning for Efficient Reasoning.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Stable Reinforcement Learning for Efficient Reasoning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.636062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e243766-bc21-46c4-87c2-c5aa4b25eeaa · outbound

This paper cites From Captions to Rewards (CAREVL): Leveraging Large Language Model Experts for Enhanced Reward Modeling in Large Vision-Language Models.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security From Captions to Rewards (CAREVL): Leveraging Large Language Model Experts for Enhanced Reward Modeling in Large Vision-Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.641313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3cf5322-1143-45bb-bd91-3e808b9497c9 · outbound

This paper cites S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.647034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc3aa545-c58a-4bb2-bbe2-0c73d2aefbce · outbound

This paper cites an unresolved cited work.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.652963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 048cc48b-0c1b-4b51-9fb7-6c9419701242 · outbound

This paper cites Raft: Reward ranked finetuning for generative foundation model alignment.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Raft: Reward ranked finetuning for generative foundation model alignment

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:09:41.119067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f1e7b308-af24-4d7f-8919-a8b2486c557c · outbound

This paper cites an unresolved cited work.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-06T12:09:41.088483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ebab30ad-0dee-4a65-835b-e9d800498ce6 · outbound

This paper cites FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.668500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f10d8a88-e333-4fd8-8961-6a1941944a2d · outbound

This paper cites The Llama 3 Herd of Models.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security The Llama 3 Herd of Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.673979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 391f5f5b-1241-4237-970e-1f42eb52cbba · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.679845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9638a436-a417-4c85-8988-bdbaa52ec948 · outbound

This paper cites The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.684858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13b317ec-4fe0-4f64-9e4a-ebec3b24439a · outbound

This paper cites an unresolved cited work.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-06T12:09:41.030510Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b88c5562-03a5-4f26-a6b7-0a5c1f784bd3 · outbound

This paper cites Break the Breakout: Reinventing LM Defense Against Jailbreak Attacks with Self-Refinement.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Break the Breakout: Reinventing LM Defense Against Jailbreak Attacks with Self-Refinement

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.696496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bd8b1a0-63cb-4b31-8fdb-9d5ce78d9dac · outbound

This paper cites an unresolved cited work.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-06T12:09:41.008162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6b470d80-6eba-4783-a5b4-51126b5557e2 · outbound

This paper cites M$^3$IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security M$^3$IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.711544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1126559f-21f4-4e64-83a8-bb3d8b427c5d · outbound

This paper cites Internal Activation Revision: Safeguarding Vision Language Models Without Parameter Update.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Internal Activation Revision: Safeguarding Vision Language Models Without Parameter Update

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-08-06T12:09:40.121101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c1538a54-558f-47c4-a7fa-2b01b5e2b5b2 · outbound

This paper cites an unresolved cited work.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-06T12:09:40.984762Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation be887a7a-fa2c-4f19-b28d-02fa7b34b7ba · outbound

This paper cites A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.727842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 126e21bd-5d1b-4911-a812-ea426c438f20 · outbound

This paper cites an unresolved cited work.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-06T12:09:40.965402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e5a05617-9a2e-4ffb-aecd-3053e2d2e054 · outbound

This paper cites an unresolved cited work.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-06T12:09:40.947573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 311feef7-41c9-4646-bf54-216b3118d6c1 · outbound

This paper cites an unresolved cited work.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-06T12:09:40.930144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 37fa36d3-ee71-4a32-b575-08e9cd19df3f · outbound

This paper cites GPT-4o System Card.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security GPT-4o System Card

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.750395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2755a9e9-8c4c-4ce0-a4b3-b13479b940ad · outbound

This paper cites GPT-4 Technical Report.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security GPT-4 Technical Report

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.755271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc56eb59-3b8a-41f1-af59-ee9a7072c07e · outbound

This paper cites an unresolved cited work.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-06T12:09:40.911616Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 984ef29e-3279-49d5-b5f9-5b00d303fbf4 · outbound

This paper cites an unresolved cited work.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-06T12:09:40.889233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 251e2a50-1a99-44ee-886a-2fe366cfdc72 · outbound

This paper cites an unresolved cited work.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.770560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c694ff11-7da1-4ce3-8281-3d35ba53fd74 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Proximal Policy Optimization Algorithms

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.776116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80dbdf6f-1f6c-4e49-8e18-0adfe99e1857 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.781262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66cc0935-f2dc-4ed9-ba1c-8bb7d93b5693 · outbound

This paper cites an unresolved cited work.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-06T12:09:40.857328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e04d1526-a757-4cf2-96b3-9ff0cce7a794 · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.791403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e9367bb-eedc-43b2-b839-06ff1e3decf3 · outbound

This paper cites an unresolved cited work.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-06T12:09:40.838177Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f2c1a692-2ea9-47bb-935f-a6eb30891e4d · outbound

This paper cites an unresolved cited work.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-08-06T12:09:40.820861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation bb329ee2-e590-48a6-99d7-403b4f066f6c · outbound

This paper cites Qwen3 Technical Report.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Qwen3 Technical Report

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.806918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84a1fa09-5fac-49a0-9a7c-5d08cfffaf94 · outbound

This paper cites SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.812263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55cf5e45-e9f1-4fbe-bd9f-960173eb29ac · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.817694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12053b92-b540-4e4e-b97b-40144ac087cf · outbound

This paper cites an unresolved cited work.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-06T12:09:40.804480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b5d488ce-ff01-4ef7-b4b2-c88ba28494c0 · outbound

This paper cites RRHF: Rank Responses to Align Language Models with Human Feedback without tears.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security RRHF: Rank Responses to Align Language Models with Human Feedback without tears

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.829280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0455717-5695-4dac-8787-f135138ddec6 · outbound

This paper cites an unresolved cited work.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Unresolved cited work

Reference 44

Resolution: unresolved; raw_fallback, observed 2026-08-06T12:09:40.786415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c11f26cd-c1b3-43d3-9d58-d93daf2f6525 · outbound

This paper cites MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.840201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3edfbbd5-0f3c-4ca0-be8e-eab2ae34accd · outbound

This paper cites an unresolved cited work.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Unresolved cited work

Reference 46

Resolution: unresolved; raw_fallback, observed 2026-08-06T12:09:40.730635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2429dbe8-2f4d-407a-ba74-8daf01e091ec · outbound

This paper cites Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.851015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d44697c-bb8e-4e2d-88ff-83c29ccf79f8 · outbound

This paper cites online" 'onlinestring :=.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security online" 'onlinestring :=

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.856064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c58aecf4-3907-4913-85f6-7e6402786a58 · outbound

This paper cites write newline.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security write newline

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.861497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 8d013345-ac84-445d-9291-df68f141e629 · inbound

FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving cites this paper.

FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:19:42.866796Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d7297b50-0c44-499a-8b65-3185c59deaa9 · inbound

FedNSAM:Consistency of Local and Global Flatness for Federated Learning cites this paper.

FedNSAM:Consistency of Local and Global Flatness for Federated Learning Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-15T18:46:29.519770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.