Paper Citation Record · LEDGER

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

As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 27 inbound Pith citation observations for arXiv:2402.02207.

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

pith.paper-citation-record.v1
2402.02207 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 27 of 27 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 27 of 27 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-08T15:38:17.335773Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T00:39:16.634455Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation d7a3d07d-855a-4e34-95f5-14b1e8d80198 · inbound

Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone cites this paper.

Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-10T20:19:27.304004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a8c50b2c-35f0-4872-aab9-a53c76c3262e · inbound

Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey cites this paper.

Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 183

Resolution: verified exact; arxiv_id, observed 2026-05-23T20:58:25.915671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5fa57646-fe9f-4fef-ae7e-95bd036355e5 · inbound

When Data Manipulation Meets Attack Goals: An In-depth Survey of Attacks for VLMs cites this paper.

When Data Manipulation Meets Attack Goals: An In-depth Survey of Attacks for VLMs Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-08T15:38:17.335773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf4c39da-e164-4a99-8e60-4ee06a4b2c4c · inbound

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

MM-RLHF: The Next Step Forward in Multimodal LLM Alignment Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-07T18:23:50.561901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1a1672a-9ef9-4020-833a-cd655bfca1ab · inbound

A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations cites this paper.

A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T19:45:18.653326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8483c4d9-565f-4c1c-a4cd-6bf3729d0d31 · inbound

Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs cites this paper.

Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-05-11T22:22:27.772873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ce6b2979-7bd1-4c8c-8804-4e63a1728c37 · inbound

VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration cites this paper.

VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T14:13:13.390836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7030a2a-6b04-40d9-aa36-666ba7ecdcdf · inbound

Seeing the Threat: Vulnerabilities in Vision-Language Models to Adversarial Attack cites this paper.

Seeing the Threat: Vulnerabilities in Vision-Language Models to Adversarial Attack Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T13:22:03.217330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb3ea9cb-e2c6-4341-a225-4e1d40090c0e · inbound

Bootstrapping LLM Robustness for VLM Safety via Reducing the Pretraining Modality Gap cites this paper.

Bootstrapping LLM Robustness for VLM Safety via Reducing the Pretraining Modality Gap Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:22.785969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8bbe007-6169-48fa-8d86-030ac4ed2cb4 · inbound

LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning cites this paper.

LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T23:59:57.357277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

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

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 bf2017b8-9f15-4b28-8d26-e7b6bd44b6bf · inbound

Attention Misses Visual Risk: Risk-Adaptive Steering for Multimodal Safety Alignment cites this paper.

Attention Misses Visual Risk: Risk-Adaptive Steering for Multimodal Safety Alignment Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T09:47:25.752076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1221b4cb-e16b-48f8-ad78-319fbd1f8d79 · inbound

VisInject: Disruption != Injection -- A Dual-Dimension Evaluation of Universal Adversarial Attacks on Vision-Language Models cites this paper.

VisInject: Disruption != Injection -- A Dual-Dimension Evaluation of Universal Adversarial Attacks on Vision-Language Models Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:56:08.104516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 50a962c4-c771-4438-98eb-8eb5bb46a5d3 · inbound

SafeSteer: A Decoding-level Defense Mechanism for Multimodal Large Language Models cites this paper.

SafeSteer: A Decoding-level Defense Mechanism for Multimodal Large Language Models Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T06:57:27.567797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 32ee3930-4fa1-4a5c-a920-8e1f3c209439 · inbound

When Vision Speaks for Sound cites this paper.

When Vision Speaks for Sound Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 78

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T22:13:46.890434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d7ac1984-15fb-4452-9c8d-85fd12cb450a · inbound

New Wide-Net-Casting Jailbreak Attacks Risk Large Models cites this paper.

New Wide-Net-Casting Jailbreak Attacks Risk Large Models Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-20T14:48:23.282107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 17dedf34-b8d5-43ac-9625-8babb5a25583 · inbound

Attention Hijacking: Response Manipulation Across Queries in Vision-Language Models cites this paper.

Attention Hijacking: Response Manipulation Across Queries in Vision-Language Models Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-05-20T14:28:21.653719Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 19a1efc1-61d2-455c-a265-ffd6b2611629 · inbound

SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment cites this paper.

SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 96

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T23:06:20.936544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7681ac16-98ff-4654-9fab-b42a903747be · inbound

Constitutional On-Policy Safe Distillation cites this paper.

Constitutional On-Policy Safe Distillation Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 57

Resolution: verified exact; arxiv_id, observed 2026-07-02T01:36:25.407430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 963082fe-a130-41cd-a8ba-16e83fc9f647 · inbound

Defending Against Malicious Finetuning by Scaling Train-time Adversarial Attacks cites this paper.

Defending Against Malicious Finetuning by Scaling Train-time Adversarial Attacks Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 28

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T20:47:22.922495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b03194f8-4fab-4c20-8960-01ce3c01d358 · inbound

Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges cites this paper.

Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 86

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T01:27:30.930139Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1e3f848c-fe44-4608-a4b8-3781ff6f3008 · inbound

ROBOSHACKLES: A Safety Dataset for Human-Injury Prevention in Embodied Foundation Models cites this paper.

ROBOSHACKLES: A Safety Dataset for Human-Injury Prevention in Embodied Foundation Models Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T00:39:16.636275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9f7c5791-3228-4039-ab3d-795e5fbf26a5 · inbound

Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs cites this paper.

Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-14T17:33:49.041193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e02f988-e635-400b-a83d-0e25b20f020b · inbound

V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure cites this paper.

V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T08:23:27.722142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0361a0a-a3ba-47dc-a2d9-4bdd3ed26e80 · inbound

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs cites this paper.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-31T23:07:40.461286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 647a6d08-e704-4322-adac-17452bb3262e · inbound

A Multimodal Automatic Redteaming Evaluation based on Atomic Jailbreak Strategy Decoupling and Combination cites this paper.

A Multimodal Automatic Redteaming Evaluation based on Atomic Jailbreak Strategy Decoupling and Combination Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 165

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:51.629463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2b8fe25-7ebe-41b8-95d7-33b9b1ea1b7a · inbound

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning cites this paper.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.797684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.