Image de couverture de livre

Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Jia, Xiaojun, Gao, Sensen, Qin, Simeng, Pang, Tianyu, Du, Chao, Huang, Yihao, Li, Xinfeng, Li, Yiming, Li, Bo, Liu, Yang
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Evolution-based Region Adversarial Prompt Learning for Robustness Enhancement in Vision-Language Models
par: Jia, Xiaojun, et autres
Publié: (2025)

Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack
par: Jia, Xiaojun, et autres
Publié: (2024)

Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs
par: Yuan, Leitao, et autres
Publié: (2026)

Adversarial Attacks Against MLLMs via Progressive Resolution Processing and Adaptive Feature Alignment
par: Wang, Haobo, et autres
Publié: (2026)

Universal Adversarial Attacks against Closed-Source MLLMs via Target-View Routed Meta Optimization
par: Lu, Hui, et autres
Publié: (2026)

Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectory
par: Gao, Sensen, et autres
Publié: (2024)

Transferable Adversarial Attacks against ASR
par: Gao, Xiaoxue, et autres
Publié: (2024)

PATFinger: Prompt-Adapted Transferable Fingerprinting against Unauthorized Multimodal Dataset Usage
par: Zhang, Wenyi, et autres
Publié: (2025)

PhysPatch: A Physically Realizable and Transferable Adversarial Patch Attack for Multimodal Large Language Models-based Autonomous Driving Systems
par: Guo, Qi, et autres
Publié: (2025)

Scale-Invariant Adversarial Attack against Arbitrary-scale Super-resolution
par: Huang, Yihao, et autres
Publié: (2025)

HTS-Attack: Heuristic Token Search for Jailbreaking Text-to-Image Models
par: Gao, Sensen, et autres
Publié: (2024)

Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models
par: Teng, Ma, et autres
Publié: (2024)

Improving Adversarial Transferability in MLLMs via Dynamic Vision-Language Alignment Attack
par: Gu, Chenhe, et autres
Publié: (2025)

Imperceptible Jailbreaking against Large Language Models
par: Gao, Kuofeng, et autres
Publié: (2025)

Making MLLMs Blind: Adversarial Smuggling Attacks in MLLM Content Moderation
par: Li, Zhiheng, et autres
Publié: (2026)

Denial-of-Service Poisoning Attacks against Large Language Models
par: Gao, Kuofeng, et autres
Publié: (2024)

Benchmarking Large Multimodal Models against Common Corruptions
par: Zhang, Jiawei, et autres
Publié: (2024)

GeoShield: Safeguarding Geolocation Privacy from Vision-Language Models via Adversarial Perturbations
par: Liu, Xinwei, et autres
Publié: (2025)

OmniSafeBench-MM: A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack-Defense Evaluation
par: Jia, Xiaojun, et autres
Publié: (2025)

Shedding Light on VLN Robustness: A Black-box Framework for Indoor Lighting-based Adversarial Attack
par: Li, Chenyang, et autres
Publié: (2025)

Improved Techniques for Optimization-Based Jailbreaking on Large Language Models
par: Jia, Xiaojun, et autres
Publié: (2024)

Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs
par: Li, Jianan, et autres
Publié: (2026)

When Memory Becomes a Vulnerability: Towards Multi-turn Jailbreak Attacks against Text-to-Image Generation Systems
par: Zhao, Shiqian, et autres
Publié: (2025)

PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models
par: Yuan, Lingzhi, et autres
Publié: (2025)

Temporal Consistency Constrained Transferable Adversarial Attacks with Background Mixup for Action Recognition
par: Li, Ping, et autres
Publié: (2025)

Defending against Patch-Based and Texture-Based Adversarial Attacks with Spectral Decomposition
par: Zhang, Wei, et autres
Publié: (2026)

Patronus: Safeguarding Text-to-Image Models against White-Box Adversaries
par: Li, Xinfeng, et autres
Publié: (2025)

CrossGuard: Safeguarding MLLMs against Joint-Modal Implicit Malicious Attacks
par: Zhang, Xu, et autres
Publié: (2025)

Improving Long-Text Alignment for Text-to-Image Diffusion Models
par: Liu, Luping, et autres
Publié: (2024)

Real-time Identity Defenses against Malicious Personalization of Diffusion Models
par: Guo, Hanzhong, et autres
Publié: (2024)

Enhancing Diffusion-based Unrestricted Adversarial Attacks via Adversary Preferences Alignment
par: Jiang, Kaixun, et autres
Publié: (2025)

ODAR: Principled Adaptive Routing for LLM Reasoning via Active Inference
par: Ma, Siyuan, et autres
Publié: (2026)

PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization
par: Cheng, Ruoxi, et autres
Publié: (2024)

MORE: Multi-Objective Adversarial Attacks on Speech Recognition
par: Gao, Xiaoxue, et autres
Publié: (2026)

AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models
par: Kang, Mintong, et autres
Publié: (2024)

FreezeVLA: Action-Freezing Attacks against Vision-Language-Action Models
par: Wang, Xin, et autres
Publié: (2025)

Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models
par: Ma, Jiachen, et autres
Publié: (2024)

DARD: Dice Adversarial Robustness Distillation against Adversarial Attacks
par: Zou, Jing, et autres
Publié: (2025)

Lifelong Safety Alignment for Language Models
par: Wang, Haoyu, et autres
Publié: (2025)

SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG
par: Si, Xiaonan, et autres
Publié: (2025)