CalvinBackup/Awesome-LVLM-Attack
1
0
Fork 0
mirror of https://github.com/liudaizong/Awesome-LVLM-Attack.git synced 2026-08-08 04:48:39 +02:00
Code Issues Packages Projects Releases Wiki Activity

update 10.27.2025

Browse Source
This commit is contained in:
Daizong Liu
2025-10-27 22:40:02 +08:00
committed by GitHub
parent 223dbe10eb
commit a895bb78ed
1 changed files with 8 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+8
View File
@@ -396,6 +396,14 @@ Here, we've summarized existing LVLM Attack methods in our survey paper👍.
* Xinzhe Huang, Wenjing Hu, Tianhang Zheng, Kedong Xiu, Xiaojun Jia, Di Wang, Zhan Qin, Kui Ren
* Zhejiang University, Nanjing University of Science and Technology, Nanyang Technological University, King Abdullah University of Science and Technology
* [Arxiv2025] https://arxiv.org/abs/2510.02999
* **Enhanced MLLM Black-Box Jailbreaking Attacks and Defenses** | #
* Xingwei Zhong, Kar Wai Fok, Vrizlynn L.L. Thing
* Cybersecurity Strategic Technology Centre
* [Arxiv2025] https://arxiv.org/abs/2510.21214
* **Beyond Text: Multimodal Jailbreaking of Vision-Language and Audio Models through Perceptually Simple Transformations** | #
* Divyanshu Kumar, Shreyas Jena, Nitin Aravind Birur, Tanay Baswa, Sahil Agarwal, Prashanth Harshangi
* Enkrypt AI
* [Arxiv2025] https://arxiv.org/abs/2510.20223
## Prompt-Injection
* **Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs** |