On the Adversarial Robustness of Visual-Language Chat Models
Open Access
- 30 June 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1118-1127
Abstract
No abstract availableFunding Information
- Natural Science Foundation of Guangdong Province (2024A1515030209, 2024A1515011970)
- National Key R&D Program of China (2023YFC3321600)
- Guangdong Basic and Applied Basic Research Foundation (2023B1515130002)
- National Natural Science Foundation of China (62376263, 62372443, 62271496)
- Shenzhen Science and Technology Innovation Commission (JCYJ20230807140507015, JCYJ20220531100804009)
This publication has 15 references indexed in Scilit:
- Benchmarking Adversarial Robustness of Image Shadow Removal with Shadow-Adaptive Attacks2024
- Discrepancy and Structure-Based Contrast for Test-Time Adaptive RetrievalIEEE Transactions on Multimedia, 2024
- On the Adversarial Robustness of Multi-Modal Foundation Models2023
- AdvDiffuser: Natural Adversarial Example Synthesis with Diffusion Models2023
- Towards Robust Rain Removal Against Adversarial Attacks: A Comprehensive Benchmark Analysis and Beyond2022
- Adversarial VQA: A New Benchmark for Evaluating the Robustness of VQA Models2021
- LAFEAT: Piercing Through Adversarial Defenses with Latent Features2021
- GPT-3: Its Nature, Scope, Limits, and ConsequencesMinds and Machines, 2020
- Deep Residual Learning for Image Recognition2016
- ImageNet: A large-scale hierarchical image database2009