Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-07T13:35:56.832563Z
Paper Citation Record · LEDGER
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
As of 20 August 2026, this Paper Citation Record lists 67 of 67 outbound references and 14 inbound Pith citation observations for arXiv:2505.21494.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-15T15:16:34.876410Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-07-09T12:56:14.862810Z
Reference resolution
67 of 67 outbound references displayed
- verified exact1
- verified fuzzy10
- unresolved54
- parse uncertain0
- malformed identifier2
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation d6d6c590-42d6-41b0-822e-10ef275b5588 · outbound
This paper cites GPT-4 Technical Report.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment GPT-4 Technical Report
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:49.458315Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 53aba7bc-ad04-4371-a30b-c53603628214 · outbound
This paper cites Flamingo: a visual language model for few-shot learning.Advances in Neural Information Processing Systems, 35: 23716–23736, 2022.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Flamingo: a visual language model for few-shot learning.Advances in Neural Information Processing Systems, 35: 23716–23736, 2022
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:49.567080Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation debd7b32-c2c1-4a71-b9b7-6aa7a6b85f88 · outbound
This paper cites PaLM 2 Technical Report.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment PaLM 2 Technical Report
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:49.671246Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4039150c-a3ae-444f-a8b0-24972fc7bc92 · outbound
This paper cites Image Hijacks: Adversarial Images can Control Generative Models at Runtime.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Image Hijacks: Adversarial Images can Control Generative Models at Runtime
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:49.779331Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f873176d-2936-4a92-920e-f26e041679cc · outbound
This paper cites Improv- ing the transferability of targeted adversarial examples through object-based diverse input.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Improv- ing the transferability of targeted adversarial examples through object-based diverse input
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T13:36:00.005359Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation d50c7d2c-baf9-477d-b570-0939cca85bf2 · outbound
This paper cites Towards evaluating the robustness of neural networks.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Towards evaluating the robustness of neural networks
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:50.024648Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 77e1130e-de80-4e79-896e-53283f08cf13 · outbound
This paper cites Are aligned neural networks adversarially aligned?.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Are aligned neural networks adversarially aligned?
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:50.164811Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cf1d090e-49ae-4a2f-8ac1-d4e618751a4b · outbound
This paper cites Rethinking Model Ensemble in Transfer-based Adversarial Attacks.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Rethinking Model Ensemble in Transfer-based Adversarial Attacks
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:50.302743Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1f2b4431-a890-4e58-93da-2020e2a032a6 · outbound
This paper cites Palm: Scaling language modeling with pathways.Journal of Machine Learning Research, 24(240): 1–113, 2023.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Palm: Scaling language modeling with pathways.Journal of Machine Learning Research, 24(240): 1–113, 2023
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T13:35:59.801185Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation f09c250d-f3f8-40b9-944f-7b788bbe851c · outbound
This paper cites A survey on multimodal large language models for autonomous driving.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment A survey on multimodal large language models for autonomous driving
Reference 10
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T13:35:59.528956Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 533f328e-9d98-4975-9baf-de628077d6f1 · outbound
This paper cites Sinkhorn distances: Lightspeed computation of optimal transport.Advances in neural information processing systems, 26, 2013.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Sinkhorn distances: Lightspeed computation of optimal transport.Advances in neural information processing systems, 26, 2013
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:50.689362Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 73af7a46-2e2e-4348-8f04-7932ad257400 · outbound
This paper cites advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorch.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorch
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:50.841588Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fab8b3b2-4a32-4dcf-b09c-6f8515aa05db · outbound
This paper cites How Robust is Google's Bard to Adversarial Image Attacks?.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment How Robust is Google's Bard to Adversarial Image Attacks?
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:50.982242Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 373cb766-e746-4356-b191-4ad9c4dd6ed6 · outbound
This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:51.083696Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 133529ae-b798-4bbb-ba8c-501f3debd4f7 · outbound
This paper cites Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
Reference 15
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:51.204470Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a5c23d5b-6673-41d0-a413-8aa5f2620c32 · outbound
This paper cites LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:51.324640Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 87b55f07-3992-464a-b753-76803431ec0f · outbound
This paper cites Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectory.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectory
Reference 17
- Resolution
- verified exact
- local_arxiv, observed 2026-08-07T13:35:57.575067Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 921febc2-46c8-4fdd-9ae1-3829b94e1aec · outbound
This paper cites Explaining and Harnessing Adversarial Examples.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Explaining and Harnessing Adversarial Examples
Reference 19
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:51.600167Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a67fab29-5b17-4fa7-8ecb-2d2a3aa6c4e2 · outbound
This paper cites Agent smith: A single image can jailbreak one million multimodal llm agents exponentially fast.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Agent smith: A single image can jailbreak one million multimodal llm agents exponentially fast
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T13:35:59.227279Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation eaea06a7-6d6a-4179-bcd4-d5652491a65b · outbound
This paper cites Countering Adversarial Images using Input Transformations.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Countering Adversarial Images using Input Transformations
Reference 21
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:51.819305Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e4e90e0d-4279-4e19-9fd2-1ff88e579ba3 · outbound
This paper cites Efficient generation of targeted and transferable adversarial examples for vision-language models via diffusion models.IEEE Transactions on Information Forensics and Security, 2024.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Efficient generation of targeted and transferable adversarial examples for vision-language models via diffusion models.IEEE Transactions on Information Forensics and Security, 2024
Reference 22
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:51.945845Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 298d6280-0ced-4e25-beb5-41c086266e93 · outbound
This paper cites OT-Attack: Enhancing Adversarial Transferability of Vision-Language Models via Optimal Transport Optimization.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment OT-Attack: Enhancing Adversarial Transferability of Vision-Language Models via Optimal Transport Optimization
Reference 23
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:52.106307Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ecdbbe7a-cca9-4aa1-9760-674bf2d4c7be · outbound
This paper cites SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentation.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentation
Reference 24
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:52.215725Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a65dbc69-8253-457c-8d16-faa8cab41031 · outbound
This paper cites Language Is Not All You Need: Aligning Perception with Language Models.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Language Is Not All You Need: Aligning Perception with Language Models
Reference 25
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:52.279416Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a5854e17-ed80-4b06-9ea0-d8fe21ed1b1f · outbound
This paper cites Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
Reference 26
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:52.404988Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 58a8fe99-1638-4ad1-ad42-378876adc7ce · outbound
This paper cites Comdefend: An efficient image compression model to defend adversarial examples.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Comdefend: An efficient image compression model to defend adversarial examples
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T13:35:59.077875Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 61b1cab7-2e3e-4b9b-b51b-1b94c1248c2b · outbound
This paper cites Natural language understanding and inference with mllm in visual question answering: A survey.ACM Computing Surveys, 57(8):1–36, 2025.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Natural language understanding and inference with mllm in visual question answering: A survey.ACM Computing Surveys, 57(8):1–36, 2025
Reference 28
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:52.599556Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6a34e8f0-e763-46c1-86b4-a2962d01d0e2 · outbound
This paper cites BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
Reference 29
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:52.680342Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 23b3972f-bd30-42bf-b519-bc4af4101549 · outbound
This paper cites VideoChat: Chat-Centric Video Understanding.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment VideoChat: Chat-Centric Video Understanding
Reference 30
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:52.839627Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b1e487e3-63f5-4fad-a7f3-e0ebddded0ca · outbound
This paper cites Improving context understanding in multimodal large language models via multimodal composition learning.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Improving context understanding in multimodal large language models via multimodal composition learning
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T13:35:58.883171Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 67fd2408-7657-47dc-80fd-02e433a518b1 · outbound
This paper cites A frustratingly simple yet highly effective attack baseline: Over 90% success rate against the strong black-box models of gpt-4.5/4o/o1.arXiv preprint arXiv:2503.10635, 2025.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment A frustratingly simple yet highly effective attack baseline: Over 90% success rate against the strong black-box models of gpt-4.5/4o/o1.arXiv preprint arXiv:2503.10635, 2025
Reference 32
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:53.099184Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3787a6af-926e-4f33-a16f-c8057a359b74 · outbound
This paper cites Enhancing Advanced Visual Reasoning Ability of Large Language Models.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Enhancing Advanced Visual Reasoning Ability of Large Language Models
Reference 33
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:53.235556Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d06aba4f-4b63-4865-833a-368c781dd20f · outbound
This paper cites Microsoft coco: Common objects in context.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Microsoft coco: Common objects in context
Reference 34
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:53.358879Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d4c1560e-d017-4d83-9100-354e2efb8419 · outbound
This paper cites Visual Instruction Tuning.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Visual Instruction Tuning
Reference 35
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:53.444061Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation df524861-71a2-4380-9ea3-11c54cc2b1ef · outbound
This paper cites Improved baselines with visual instruction tuning.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Improved baselines with visual instruction tuning
Reference 36
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:53.528417Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cccdc95a-89aa-4648-9e47-aaf4bb2cc0e4 · outbound
This paper cites Safety of Multimodal Large Language Models on Images and Texts.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Safety of Multimodal Large Language Models on Images and Texts
Reference 37
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:53.646908Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7730ddf2-4184-494a-a4b0-0763b5c50bca · outbound
This paper cites Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study
Reference 38
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:53.728471Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 30817079-a523-4f02-92f4-a08dc790a7db · outbound
This paper cites Frequency domain model augmentation for adversarial attack.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Frequency domain model augmentation for adversarial attack
Reference 39
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:53.862054Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7a66557e-295c-44d8-a4b5-c70850689098 · outbound
This paper cites Questioning, answering, and captioning for zero-shot detailed image caption.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Questioning, answering, and captioning for zero-shot detailed image caption
Reference 40
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T13:35:58.732394Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 051b4a18-41c9-48cb-afad-412c5ced3412 · outbound
This paper cites Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models
Reference 41
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:54.066433Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d82267be-1595-454c-b0c4-e8fdd0f97725 · outbound
This paper cites Towards Deep Learning Models Resistant to Adversarial Attacks.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Towards Deep Learning Models Resistant to Adversarial Attacks
Reference 42
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:54.172351Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 046113fe-17c2-41ff-af41-47069a38b3b9 · outbound
This paper cites Training language models to follow instructions with human feedback.Advances in Neural Information Processing Systems, 35:27730–27744, 2022.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Training language models to follow instructions with human feedback.Advances in Neural Information Processing Systems, 35:27730–27744, 2022
Reference 43
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:54.277385Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b82bf650-0879-43e3-8872-4fd8ccc39a5f · outbound
This paper cites Red Teaming Language Models with Language Models.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Red Teaming Language Models with Language Models
Reference 44
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:54.349572Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b6913d6d-2efe-4ffd-8948-bf8520245544 · outbound
This paper cites Learning transferable visual models from natural language supervision.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Learning transferable visual models from natural language supervision
Reference 45
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:54.443770Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 184826b5-a3fe-4e46-b094-04f2eb32be00 · outbound
This paper cites Image Captioning Evaluation in the Age of Multimodal LLMs: Challenges and Future Perspectives.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Image Captioning Evaluation in the Age of Multimodal LLMs: Challenges and Future Perspectives
Reference 46
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:54.549170Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6f82d06b-9593-4a8f-b71d-ef1caed492b3 · outbound
This paper cites BLOOM: A 176B-Parameter Open-Access Multilingual Language Model.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Reference 47
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:54.659888Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 07540c05-12cb-4f1c-b301-a6e7051a9fe8 · outbound
This paper cites On the adversarial robustness of multi-modal founda- tion models.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment On the adversarial robustness of multi-modal founda- tion models
Reference 48
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:54.845752Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fa667496-da25-46f1-8041-c67904e0c053 · outbound
This paper cites PandaGPT: One Model To Instruction-Follow Them All.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment PandaGPT: One Model To Instruction-Follow Them All
Reference 49
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:54.954745Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c570df1d-1fa9-4844-bc50-6962a1af0081 · outbound
This paper cites LLaMA: Open and Efficient Foundation Language Models.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment LLaMA: Open and Efficient Foundation Language Models
Reference 50
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:55.040125Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 237911bb-7dd7-4e92-9109-59936103a8e5 · outbound
This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Llama 2: Open Foundation and Fine-Tuned Chat Models
Reference 51
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:55.132411Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d9988ab8-1bc9-4f7c-a53c-e55133945edb · outbound
This paper cites Multimodal few-shot learning with frozen language models.Advances in Neural Information Processing Systems, 34:200–212, 2021.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Multimodal few-shot learning with frozen language models.Advances in Neural Information Processing Systems, 34:200–212, 2021
Reference 52
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:55.254426Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cf22a302-1e01-4e57-b838-dfdc96986a09 · outbound
This paper cites How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs
Reference 53
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:55.414755Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b25bbc94-ba7f-4cd9-9b70-0e19cf893dba · outbound
This paper cites Springer, 2009.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Springer, 2009
Reference 54
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:55.501406Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8311a177-207b-4aaa-be9e-ff012ab7ce2b · outbound
This paper cites InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models
Reference 55
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:55.625791Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cf193db2-d84d-4f48-897e-ebee42b7be9a · outbound
This paper cites Black-box sparse adversarial attack via multi-objective optimisation.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Black-box sparse adversarial attack via multi-objective optimisation
Reference 56
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T13:35:58.611990Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 9a79c70a-161c-46af-9692-6c381a109884 · outbound
This paper cites Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models
Reference 57
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:55.844596Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8972e13b-5038-458c-90c2-34d09d3499e8 · outbound
This paper cites An empirical study of gpt-3 for few-shot knowledge-based vqa.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment An empirical study of gpt-3 for few-shot knowledge-based vqa
Reference 58
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T13:35:58.453771Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 9c5b7731-6173-402f-bac8-5f34f612c299 · outbound
This paper cites AnyAttack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment AnyAttack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models
Reference 59
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:55.980677Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b088cfe2-7099-4481-9238-10f15653e530 · outbound
This paper cites On Evaluating Adversarial Robustness of Large Vision-Language Models.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment On Evaluating Adversarial Robustness of Large Vision-Language Models
Reference 60
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:56.073322Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c82e27a2-fcc2-4b7a-9455-2e7e870501b1 · outbound
This paper cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
Reference 61
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:56.169643Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 49f3875c-3f69-4970-91e3-01b9fe572376 · outbound
This paper cites Boosting transferability of targeted adversarial examples with non-robust feature alignment.Expert Systems with Applications, 227:120248, 2023.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Boosting transferability of targeted adversarial examples with non-robust feature alignment.Expert Systems with Applications, 227:120248, 2023
Reference 62
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T13:35:58.180366Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 02365128-d5a3-4427-853b-65671b5f5a03 · outbound
This paper cites PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts
Reference 63
- Resolution
- malformed identifier
- no resolver link, observed 2026-08-07T13:35:56.355578Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4e3ec945-1a16-4750-9926-157e393c97ba · outbound
This paper cites an unresolved cited work.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Unresolved cited work
Reference 64
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:56.434228Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 66e458ea-c708-46e0-ac33-0e1342c1c617 · outbound
This paper cites an unresolved cited work.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Unresolved cited work
Reference 65
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:56.529699Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9102bc7d-9cd1-4e9f-9cdb-cb94c64b4694 · outbound
This paper cites Focus on **whether both descriptions fundamentally describe the same thing.**.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Focus on **whether both descriptions fundamentally describe the same thing.**
Reference 66
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:56.615468Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7ad76c61-c4b0-44d4-94bc-a818c5a2ba9a · outbound
This paper cites an unresolved cited work.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Unresolved cited work
Reference 67
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:35:56.727415Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e8aa0a1f-03e6-45f3-9920-6fe284f78bb6 · outbound
This paper cites {input_text_1}.
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment {input_text_1}
Reference 68
- Resolution
- malformed identifier
- raw_fallback, observed 2026-08-07T13:35:57.923750Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Pith citing papers
Observation a035745a-d293-41b7-8b98-5a9cef997ecb · inbound
3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation cites this paper.
3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
Reference 24
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T20:58:51.899166Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 52dcbe22-e334-4464-890f-9786224efb40 · inbound
Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models cites this paper.
Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T16:15:27.911200Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 49bd0555-2734-4236-a374-51874690cb3c · inbound
Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP cites this paper.
Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
Reference 2019
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T07:47:37.534486Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8a86ff78-7cc6-4025-aba1-4b0d1c0c270c · inbound
Universal Adversarial Attacks against Closed-Source MLLMs via Target-View Routed Meta Optimization cites this paper.
Universal Adversarial Attacks against Closed-Source MLLMs via Target-View Routed Meta Optimization Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
Reference 6
- Resolution
- verified exact
- arxiv_id, observed 2026-05-16T09:27:40.973099Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation b7cf3046-9cbb-4aa6-969c-a972b9a70890 · inbound
Mosaic: Multimodal Jailbreak against Closed-Source VLMs via Multi-View Ensemble Optimization cites this paper.
Mosaic: Multimodal Jailbreak against Closed-Source VLMs via Multi-View Ensemble Optimization Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
Reference 13
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T05:35:59.178907Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 50504f78-419d-4279-a532-7846a7ccc129 · inbound
Adversarial Attacks Against MLLMs via Progressive Resolution Processing and Adaptive Feature Alignment cites this paper.
Adversarial Attacks Against MLLMs via Progressive Resolution Processing and Adaptive Feature Alignment Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
Reference 26
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T06:21:27.955839Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation b6f53335-55b6-46a9-9415-5f5118429e7c · inbound
DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models cites this paper.
DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
Reference 22
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T18:33:37.919303Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation c77dc30e-d393-4c5b-91c3-47d074ce88e6 · inbound
CogniVerse: Revolutionizing Multi-Modal Retrieval-Augmented Generation with Cognitive Reflection and Geometric Reasoning cites this paper.
CogniVerse: Revolutionizing Multi-Modal Retrieval-Augmented Generation with Cognitive Reflection and Geometric Reasoning Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
Reference 62
- Resolution
- verified exact
- arxiv_id, observed 2026-06-29T08:23:15.763386Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 66e48b9e-d251-4a04-ac7d-ecc359911ffe · inbound
REALM: A Unified Red-Teaming Benchmark for Physical-World VLMs cites this paper.
REALM: A Unified Red-Teaming Benchmark for Physical-World VLMs Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
Reference 15
- Resolution
- verified exact
- arxiv_id, observed 2026-07-04T10:29:45.732836Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation aa01307b-df84-46ea-bef2-bf5abc3ae45a · inbound
MIRAGE: Protecting against Malicious Image Editing via False Moderation cites this paper.
MIRAGE: Protecting against Malicious Image Editing via False Moderation Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
Reference 32
- Resolution
- verified exact
- arxiv_id, observed 2026-07-04T15:09:54.649235Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 9268db2d-a89a-4bb6-9779-924540dce770 · inbound
MIRAGE: Protecting against Malicious Image Editing via False Moderation cites this paper.
MIRAGE: Protecting against Malicious Image Editing via False Moderation Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
Reference 32
- Resolution
- verified exact
- arxiv_id, observed 2026-06-29T19:13:53.523673Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 56724a41-4eb3-4444-bf07-4892ab00bc0f · inbound
XPlainVerse: A Million-Scale Benchmark for Explainable Deepfake Detection cites this paper.
XPlainVerse: A Million-Scale Benchmark for Explainable Deepfake Detection Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-07-12T01:35:43.979206Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 02808c47-6ced-4729-bbde-4aaa411a6f22 · inbound
On Adversarial Vulnerability of Vision-Language Models through the Lens of Intermediate Spectral Subspaces cites this paper.
On Adversarial Vulnerability of Vision-Language Models through the Lens of Intermediate Spectral Subspaces Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
Reference 37
- Resolution
- verified exact
- local_arxiv, observed 2026-07-09T12:56:14.864124Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 080750ee-020a-4eec-805f-fbe337f85dc8 · inbound
Fighting Fire with Fire: On the Feasibility of Protecting Exercises Against AI Cheating cites this paper.
Fighting Fire with Fire: On the Feasibility of Protecting Exercises Against AI Cheating Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T15:16:34.876410Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.