ResearchTrend.AI
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment

Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment

Xiaojun Jia
Sensen Gao
Simeng Qin
Tianyu Pang
C. Du
Yihao Huang
Xinfeng Li
Yiming Li
Bo Li
Wenshu Fan
    AAML
ArXiv (abs)PDFHTMLHuggingFace (8 upvotes)

Papers citing "Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment"

11 / 11 papers shown
When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Models
When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Models
Hui Lu
Yi Yu
Yiming Yang
Chenyu Yi
Qixin Zhang
Bingquan Shen
Alex Chichung Kot
Xudong Jiang
AAML
466
0
0
26 Nov 2025
On the Feasibility of Hijacking MLLMs' Decision Chain via One Perturbation
On the Feasibility of Hijacking MLLMs' Decision Chain via One Perturbation
Changyue Li
Jiaying Li
Youliang Yuan
Jiaming He
Zhicong Huang
Pinjia He
AAML
240
0
0
25 Nov 2025
DualTAP: A Dual-Task Adversarial Protector for Mobile MLLM Agents
DualTAP: A Dual-Task Adversarial Protector for Mobile MLLM Agents
Fuyao Zhang
Jiaming Zhang
C. Wang
Xiongtao Sun
Yurong Hao
Guowei Guan
Wenjie Li
Longtao Huang
Wei Yang Bryan Lim
AAML
181
0
0
17 Nov 2025
Black-box Optimization of LLM Outputs by Asking for Directions
Black-box Optimization of LLM Outputs by Asking for Directions
Jie Zhang
Meng Ding
Yang Liu
Jue Hong
F. Tramèr
AAML
154
0
0
19 Oct 2025
Kelp: A Streaming Safeguard for Large Models via Latent Dynamics-Guided Risk Detection
Kelp: A Streaming Safeguard for Large Models via Latent Dynamics-Guided Risk Detection
Xiaodan Li
Mengjie Wu
Yao Zhu
Yunna Lv
YueFeng Chen
Cen Chen
Jianmei Guo
H. Xue
KELM
177
0
0
09 Oct 2025
Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models
Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models
Rui Zhang
Z. Wang
Tianli Yang
Hongwei Li
Wenbo Jiang
Qingchuan Zhao
Wenshu Fan
Guowen Xu
AAMLVLM
83
1
0
26 Aug 2025
GeoShield: Safeguarding Geolocation Privacy from Vision-Language Models via Adversarial Perturbations
GeoShield: Safeguarding Geolocation Privacy from Vision-Language Models via Adversarial Perturbations
Xinwei Liu
Xiaojun Jia
Yuan Xun
Simeng Qin
Simeng Qin
AAML
369
1
0
05 Aug 2025
3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation
3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation
Tianrui Lou
Xiaojun Jia
Yaning Tan
Jiawei Liang
Ming Zhang
Yanjun Xiao
Xiaochun Cao
3DGSAAML
221
0
0
02 Jul 2025
Image Captioning Evaluation in the Age of Multimodal LLMs: Challenges and Future Perspectives
Image Captioning Evaluation in the Age of Multimodal LLMs: Challenges and Future PerspectivesInternational Joint Conference on Artificial Intelligence (IJCAI), 2024
Sara Sarto
Marcella Cornia
Rita Cucchiara
367
6
0
18 Mar 2025
A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1
A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1
Zhaoyi Li
Xiaohan Zhao
Dong-Dong Wu
Jiacheng Cui
Zhiqiang Shen
AAMLVLM
519
8
0
13 Mar 2025
Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
Hao Wu
Bohan Jia
Zijie Zhai
Shaosheng Cao
Zheyu Ye
Fei Zhao
Zhe Xu
Yao Hu
Shaohui Lin
MUOffRLLRMMLLMReLMVLM
580
361
0
09 Mar 2025