Paper Citation Record · LEDGER

Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 26 inbound Pith citation observations for arXiv:2307.14539.

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

pith.paper-citation-record.v1
2307.14539 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 26 of 26 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 26 of 26 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-08T11:17:01.681810Z

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

11
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 93eb2451-001a-4e1a-a8c2-9236cb04e23e · inbound

Adversarial Hubness in Multi-Modal Retrieval cites this paper.

Adversarial Hubness in Multi-Modal Retrieval Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 64

Resolution: verified exact; arxiv_id, observed 2026-05-23T06:42:39.697999Z

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 780e3805-7313-4a42-8263-d1977ff01bf1 · inbound

Universal Adversarial Attack on Aligned Multimodal LLMs cites this paper.

Universal Adversarial Attack on Aligned Multimodal LLMs Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-08T11:17:01.681810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 640678cd-a03e-41a8-b33a-01dfcf983ed4 · 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 Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T13:22:02.564374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af023c88-0c17-4978-99fc-96cd4461ca92 · inbound

System Prompt Extraction Attacks and Defenses in Large Language Models cites this paper.

System Prompt Extraction Attacks and Defenses in Large Language Models Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T13:28:18.153671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 935f29c8-819d-44e0-9ed8-0b5acf5b550a · inbound

Towards LLM-Centric Multimodal Fusion: A Survey on Integration Strategies and Techniques cites this paper.

Towards LLM-Centric Multimodal Fusion: A Survey on Integration Strategies and Techniques Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T10:36:56.201686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f774a9d4-d82c-4377-99ac-5ce50c7c1e4f · inbound

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 cites this paper.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.767811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d32e28a-e4c4-43df-ae85-041e806c17e8 · inbound

MGC: A Compiler Framework Exploiting Compositional Blindness in Aligned LLMs for Malware Generation cites this paper.

MGC: A Compiler Framework Exploiting Compositional Blindness in Aligned LLMs for Malware Generation Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T20:45:53.336749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6565244e-3082-400d-8c66-a9983a9a5b07 · inbound

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models cites this paper.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:55.054008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82a3f87e-8bec-4c3a-ad79-7b6a7ece17f2 · inbound

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

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 112

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:43.341604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc99b17a-ccf1-47a6-8a7e-b1a1b339aa4a · inbound

On Surjectivity of Neural Networks: Can you elicit any behavior from your model? cites this paper.

On Surjectivity of Neural Networks: Can you elicit any behavior from your model? Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-05T16:00:48.920892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54bd8f24-2f21-4381-870a-fa1e1b82fc8b · inbound

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models cites this paper.

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T13:45:27.193722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ccf2f37-4e96-4f15-bf23-8924c449d2e0 · inbound

Breaking the Illusion: Consensus-Based Generative Mitigation of Adversarial Illusions in Multi-Modal Embeddings cites this paper.

Breaking the Illusion: Consensus-Based Generative Mitigation of Adversarial Illusions in Multi-Modal Embeddings Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-17T04:19:00.653543Z

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 0ad3e127-d318-410f-a13b-3278926e7317 · inbound

When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models cites this paper.

When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T01:22:20.544698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4eced2e-1865-4dd7-82bf-e0d3984f9044 · inbound

Visual Inception: Compromising Long-term Planning in Agentic Recommenders via Multimodal Memory Poisoning cites this paper.

Visual Inception: Compromising Long-term Planning in Agentic Recommenders via Multimodal Memory Poisoning Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T06:31:30.397970Z

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 f0fd111e-23b7-46f7-a0c3-11fc3e35094f · inbound

LLM-as-Judge Framework for Evaluating Tone-Induced Hallucination in Vision-Language Models cites this paper.

LLM-as-Judge Framework for Evaluating Tone-Induced Hallucination in Vision-Language Models Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-10T09:38:43.135564Z

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 2279d4f5-ccee-4e80-a631-091978570ad4 · 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 Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:56:08.100467Z

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 0116a73f-dbd9-41f1-8b75-542ead80ea15 · inbound

Hard to Read, Easy to Jailbreak: How Visual Degradation Bypasses MLLM Safety Alignment cites this paper.

Hard to Read, Easy to Jailbreak: How Visual Degradation Bypasses MLLM Safety Alignment Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-05-11T04:15:55.435798Z

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 8052a9a8-493d-4cda-a2df-a552d21ad949 · inbound

Cross-Modal Backdoors in Multimodal Large Language Models cites this paper.

Cross-Modal Backdoors in Multimodal Large Language Models Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-11T04:20:55.560053Z

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 531c9269-01a0-452a-b5e3-a0d7555a4245 · 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 Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T06:57:27.579290Z

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 80e72eca-b20d-40c2-9abd-b0f45c1b38a8 · inbound

Hierarchical Attacks for Multi-Modal Multi-Agent Reasoning cites this paper.

Hierarchical Attacks for Multi-Modal Multi-Agent Reasoning Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:19:27.866072Z

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 3156071d-2d3f-4048-800e-7750b7c068ed · inbound

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

New Wide-Net-Casting Jailbreak Attacks Risk Large Models Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-20T14:48:23.305879Z

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 b66006b8-37eb-4a44-a821-26a3dc76a22b · inbound

StructBreak: Structural Cognitive Overload-Induced Safety Failures in MLLMs cites this paper.

StructBreak: Structural Cognitive Overload-Induced Safety Failures in MLLMs Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T22:14:00.307459Z

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 53758016-6a28-42fd-8bbd-03bc621c485f · inbound

Exploring Adversarial Robustness and Safety Alignment in Multilingual Multi-Modal Large Language Models cites this paper.

Exploring Adversarial Robustness and Safety Alignment in Multilingual Multi-Modal Large Language Models Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-07-02T03:16:34.800540Z

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 793dd131-8a65-4a89-a6c8-5f914fcb42b7 · inbound

MLingualFC: Evaluating Jailbreak Vulnerabilities in Multilingual Vision-Language Models cites this paper.

MLingualFC: Evaluating Jailbreak Vulnerabilities in Multilingual Vision-Language Models Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 106

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T18:57:16.807009Z

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 ff6621f4-fd71-469c-bcb9-17f2a9b1a530 · 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 Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 59

Resolution: metadata mismatch; arxiv_id, observed 2026-06-26T04:38:59.187160Z

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 f6ef984f-de2c-4048-bb30-f9b3eb3041fc · inbound

One Modality to Forget Them All: Enhancing Cross-Modal Unlearning in Vision-Language Models cites this paper.

One Modality to Forget Them All: Enhancing Cross-Modal Unlearning in Vision-Language Models Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-01T21:01:07.095663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.