Paper Citation Record · LEDGER

Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 24 inbound Pith citation observations for arXiv:2403.09792.

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

pith.paper-citation-record.v1
2403.09792 v3

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 24 of 24 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 24 of 24 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T10:29:59.102631Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 2f5e0070-c549-441a-b512-22ea6ab8afed · inbound

Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents cites this paper.

Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Reference 144

Resolution: unresolved; no resolver link, observed 2026-08-12T20:36:01.981964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8e24227-ecba-4979-b7fd-1e241c30071a · inbound

Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks cites this paper.

Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-12T14:24:32.496011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f161ed69-38a0-42b8-9894-018d2f5eab71 · inbound

Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models cites this paper.

Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T11:40:22.113488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 730ab023-5738-46d0-945c-4f5b52845128 · inbound

Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models cites this paper.

Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T20:17:02.680795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f91c0b38-67c7-4d24-b96e-66b0aeb018a8 · inbound

A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges cites this paper.

A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Reference 130

Resolution: unresolved; no resolver link, observed 2026-08-10T22:17:23.309189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e75ffcd5-7b88-451e-ae13-4328eb288cd2 · inbound

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency cites this paper.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.556069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 162f2e74-2f07-4a9b-9095-b603a7cd183a · inbound

MSTS: A Multimodal Safety Test Suite for Vision-Language Models cites this paper.

MSTS: A Multimodal Safety Test Suite for Vision-Language Models Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T19:27:42.247438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bf3f076-3aa4-400d-a15d-5c9e7dafadb9 · inbound

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models cites this paper.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.310173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9231a06-af04-49cc-ba6a-af6d09090d4e · inbound

Robust-LLaVA: On the Effectiveness of Large-Scale Robust Image Encoders for Multi-modal Large Language Models cites this paper.

Robust-LLaVA: On the Effectiveness of Large-Scale Robust Image Encoders for Multi-modal Large Language Models Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-09T14:58:53.792111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa29efff-feab-44d5-850d-a51af125e94f · 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 Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T19:45:18.507649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5c0eedf-30c6-4bb5-8717-2426ff33417c · inbound

DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models cites this paper.

DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:59.102631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bbb22b3-c3e5-4fb6-9e72-e6ca0e43ee60 · inbound

Exploring Jailbreak Attacks on LLMs through Intent Concealment and Diversion cites this paper.

Exploring Jailbreak Attacks on LLMs through Intent Concealment and Diversion Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T15:41:11.420668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b98ecd05-61e7-4851-ac8c-c2ab05677a56 · inbound

Backdoor Cleaning without External Guidance in MLLM Fine-tuning cites this paper.

Backdoor Cleaning without External Guidance in MLLM Fine-tuning Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T14:56:51.412320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a43af3d-bcb8-4cfb-9482-2b6cd603c2ae · 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 Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T13:22:01.312248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43c65426-d610-4b47-a5df-062d796a065b · inbound

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation cites this paper.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Reference 114

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:43.497004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ce15541-625c-495a-ab08-158e850576cd · inbound

SALLIE: Generation-Free Hidden-State Detection of Jailbreaks and Prompt Injections Across Text and Vision cites this paper.

SALLIE: Generation-Free Hidden-State Detection of Jailbreaks and Prompt Injections Across Text and Vision Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T23:30:51.245712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 2f9908e5-36b1-4c44-96d3-04107195ea7e · inbound

Gaslight, Gatekeep, V1-V3: Early Visual Cortex Alignment Shields Vision-Language Models from Sycophantic Manipulation cites this paper.

Gaslight, Gatekeep, V1-V3: Early Visual Cortex Alignment Shields Vision-Language Models from Sycophantic Manipulation Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Reference 44

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T13:10:26.165165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 756304eb-f199-48c5-ad30-710f8f78ad83 · 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 Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T16:56:08.176963Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 8469b9c3-1e1f-498e-8828-843be58a7a9f · inbound

Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing cites this paper.

Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-05-12T05:51:27.478710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 99fd1219-c007-4303-b66d-521a0bbd0d06 · inbound

EVA: Editing for Versatile Alignment against Jailbreaks cites this paper.

EVA: Editing for Versatile Alignment against Jailbreaks Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T14:35:47.008475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ac30a608-caba-4506-af9e-8b6353e1c10a · inbound

VisualLeakBench: Reproducible Action-Boundary Propagation Failures in Vision-Language Agents cites this paper.

VisualLeakBench: Reproducible Action-Boundary Propagation Failures in Vision-Language Agents Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-06-28T23:02:46.383448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f88c73f7-be16-451e-a3ac-d9fbafd23c98 · inbound

Adversarial Diffusion Across Modalities: A Fusion Survey of Attacks, Defenses, and Evaluation for Text, Vision, and Vision-Language Models cites this paper.

Adversarial Diffusion Across Modalities: A Fusion Survey of Attacks, Defenses, and Evaluation for Text, Vision, and Vision-Language Models Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Reference 31

Resolution: metadata mismatch; arxiv_id, observed 2026-06-26T04:38:59.195293Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 56e80f9a-1140-4f7e-883e-db34e857a2e8 · 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 Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Reference 130

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:48.340224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b330890a-6d8b-4c62-a945-a091af957280 · inbound

SafeCap: Improving LVLM Safety with Image Captioning Reinforcement Learning cites this paper.

SafeCap: Improving LVLM Safety with Image Captioning Reinforcement Learning Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-15T14:24:49.628739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.