Image de couverture de livre

Less Is More -- Until It Breaks: Security Pitfalls of Vision Token Compression in Large Vision-Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Xiaomei, Zhang, Zhaoxi, Zhang, Leo Yu, Zhang, Yanjun, Tao, Guanhong, Pan, Shirui
Format:	Preprint
Publié:	2026
Sujets:	Cryptography and Security Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Large Language Model Watermark Stealing With Mixed Integer Programming
par: Zhang, Zhaoxi, et autres
Publié: (2024)

Character-Level Perturbations Disrupt LLM Watermarks
par: Zhang, Zhaoxi, et autres
Publié: (2025)

Masked Language Model Based Textual Adversarial Example Detection
par: Zhang, Xiaomei, et autres
Publié: (2023)

The Security Threat of Compressed Projectors in Large Vision-Language Models
par: Zhang, Yudong, et autres
Publié: (2025)

On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression
par: Zhang, Xinwei, et autres
Publié: (2026)

When Better Features Mean Greater Risks: The Performance-Privacy Trade-Off in Contrastive Learning
par: Sun, Ruining, et autres
Publié: (2025)

Not All Edges are Equally Robust: Evaluating the Robustness of Ranking-Based Federated Learning
par: Gong, Zirui, et autres
Publié: (2025)

CodeBC: A More Secure Large Language Model for Smart Contract Code Generation in Blockchain
par: Wang, Lingxiang, et autres
Publié: (2025)

Backdoor Attacks and Defenses in Computer Vision Domain: A Survey
par: Abbasi, Bilal Hussain, et autres
Publié: (2025)

Towards Model Extraction Attacks in GAN-Based Image Translation via Domain Shift Mitigation
par: Mi, Di, et autres
Publié: (2024)

ClawLess: A Security Model of AI Agents
par: Lu, Hongyi, et autres
Publié: (2026)

Automating Security Audit Using Large Language Model based Agent: An Exploration Experiment
par: Chin, Jia Hui, et autres
Publié: (2025)

NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models
par: Zhang, Chuhan, et autres
Publié: (2025)

VeriLoRA: Fine-Tuning Large Language Models with Verifiable Security via Zero-Knowledge Proofs
par: Liao, Guofu, et autres
Publié: (2025)

Membership Inference Attacks on Tokenizers of Large Language Models
par: Tong, Meng, et autres
Publié: (2025)

Multi-PA: A Multi-perspective Benchmark on Privacy Assessment for Large Vision-Language Models
par: Zhang, Jie, et autres
Publié: (2024)

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities
par: Qu, Yiting, et autres
Publié: (2025)

Membership Inference Attacks Against Vision-Language Models
par: Hu, Yuke, et autres
Publié: (2025)

Safety Layers in Aligned Large Language Models: The Key to LLM Security
par: Li, Shen, et autres
Publié: (2024)

Credential Leakage in LLM Agent Skills: A Large-Scale Empirical Study
par: Chen, Zhihao, et autres
Publié: (2026)

ARES: Scalable and Practical Gradient Inversion Attack in Federated Learning through Activation Recovery
par: Gong, Zirui, et autres
Publié: (2026)

Fluent: Round-efficient Secure Aggregation for Private Federated Learning
par: Li, Xincheng, et autres
Publié: (2024)

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation
par: Zhong, Zhiyuan, et autres
Publié: (2025)

Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring
par: Hua, Peichun, et autres
Publié: (2025)

What Breaks Embodied AI Security:LLM Vulnerabilities, CPS Flaws,or Something Else?
par: Ma, Boyang, et autres
Publié: (2026)

SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models
par: Zhang, Jiawen, et autres
Publié: (2025)

LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models
par: Yu, Miao, et autres
Publié: (2024)

SoK: Taxonomy and Evaluation of Prompt Security in Large Language Models
par: Hong, Hanbin, et autres
Publié: (2025)

A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly
par: Yao, Yifan, et autres
Publié: (2023)

Large Language Model-driven Security Assistant for Internet of Things via Chain-of-Thought
par: Zeng, Mingfei, et autres
Publié: (2025)

A Sentence Relation-Based Approach to Sanitizing Malicious Instructions
par: Datta, Soumil, et autres
Publié: (2026)

An Engorgio Prompt Makes Large Language Model Babble on
par: Dong, Jianshuo, et autres
Publié: (2024)

A Survey on Data Security in Large Language Models
par: Chen, Kang, et autres
Publié: (2025)

Agora: Trust Less and Open More in Verification for Confidential Computing
par: Chen, Hongbo, et autres
Publié: (2024)

(Security) Assertions by Large Language Models
par: Kande, Rahul, et autres
Publié: (2023)

Token Inflation: How Dishonest Providers Can Overcharge for Large Language Model Usage
par: Hoque, Shahinul, et autres
Publié: (2026)

Disrupting Vision-Language Model-Driven Navigation Services via Adversarial Object Fusion
par: Xie, Chunlong, et autres
Publié: (2025)

SNARE: Adaptive Scenario Synthesis for Eliciting Overeager Behavior in Coding Agents
par: Qu, Yubin, et autres
Publié: (2026)

Vaporizer: Breaking Watermarking Schemes for Large Language Model Outputs
par: Ng, Jonathan Hong Jin, et autres
Publié: (2026)

Breaking Minds, Breaking Systems: Jailbreaking Large Language Models via Human-like Psychological Manipulation
par: Liu, Zehao, et autres
Publié: (2025)