{"total":14,"rows":[{"id":"2204.03972","title":"Contrastive language and vision learning of general fashion concepts","created":"2022-04-08","cited_by_count":42,"area":null},{"id":"2402.06244","title":"Quantifying and Enhancing Multi-modal Robustness with Modality Preference","created":"2024-02-09","cited_by_count":16,"area":null},{"id":"2312.12768","title":"Mutual-modality Adversarial Attack with Semantic Perturbation","created":"2023-12-20","cited_by_count":14,"area":null},{"id":"2308.14597","title":"Adversarial Attacks on Foundational Vision Models","created":"2023-08-28","cited_by_count":13,"area":null},{"id":"2403.12693","title":"As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?","created":"2024-03-19","cited_by_count":11,"area":null},{"id":"2508.20546","title":"MM-HSD: Multi-Modal Hate Speech Detection in Videos","created":"2025-08-28","cited_by_count":5,"area":null},{"id":"2406.03728","title":"Evaluating Durability: Benchmark Insights into Multimodal Watermarking","created":"2024-06-06","cited_by_count":3,"area":null},{"id":"2407.21174","title":"AI Safety in Practice: Enhancing Adversarial Robustness in Multimodal Image Captioning","created":"2024-07-30","cited_by_count":3,"area":null},{"id":"2307.03798","title":"Fooling Contrastive Language-Image Pre-trained Models with CLIPMasterPrints","created":"2023-07-07","cited_by_count":2,"area":null},{"id":"2405.17678","title":"TIMA: Text-Image Mutual Awareness for Balancing Zero-Shot Adversarial Robustness and Generalization Ability","created":"2024-05-27","cited_by_count":2,"area":null},{"id":"2506.05394","title":"Attacking Attention of Foundation Models Disrupts Downstream Tasks","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2310.00503","title":"Black-box Attacks on Image Activity Prediction and its Natural Language Explanations","created":"2023-09-30","cited_by_count":1,"area":null},{"id":"2511.05325","title":"Turning Adversaries into Allies: Reversing Typographic Attacks for Multimodal E-Commerce Product Retrieval","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2511.06947","title":"FoCLIP: A Feature-Space Misalignment Framework for CLIP-Based Image Manipulation and Detection","created":"2025-11-10","cited_by_count":0,"area":null}],"next_cursor":null}