Cover Image

One Single Hub Text Breaks CLIP: Identifying Vulnerabilities in Cross-Modal Encoders via Hubness

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Deguchi, Hiroyuki, Chousa, Katsuki, Sakai, Yusuke
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence Cryptography and Security Information Retrieval
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Hacking Neural Evaluation Metrics with Single Hub Text
by: Deguchi, Hiroyuki, et al.
Published: (2025)

Adversarial Hubness in Multi-Modal Retrieval
by: Zhang, Tingwei, et al.
Published: (2024)

BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models
by: Xue, Jiaqi, et al.
Published: (2024)

CellularLint: A Systematic Approach to Identify Inconsistent Behavior in Cellular Network Specifications
by: Rahman, Mirza Masfiqur, et al.
Published: (2024)

Token-wise Influential Training Data Retrieval for Large Language Models
by: Lin, Huawei, et al.
Published: (2024)

DiscourseFlip: An Oblique Discourse-Level Opinion Manipulation Attack against Black-box Retrieval-Augmented Generation
by: Gong, Yuyang, et al.
Published: (2026)

PII-Bench: Evaluating Query-Aware Privacy Protection Systems
by: Shen, Hao, et al.
Published: (2025)

Improving User Privacy in Personalized Generation: Client-Side Retrieval-Augmented Modification of Server-Side Generated Speculations
by: Salemi, Alireza, et al.
Published: (2026)

SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions
by: Mishra, Saroj, et al.
Published: (2026)

TITAN: Graph-Executable Reasoning for Cyber Threat Intelligence
by: Simoni, Marco, et al.
Published: (2025)

Exposing Citation Vulnerabilities in Generative Engines
by: Mochizuki, Riku, et al.
Published: (2025)

Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models via Reasoning
by: Guo, Junfeng, et al.
Published: (2025)

VulReaD: Knowledge-Graph-guided Software Vulnerability Reasoning and Detection
by: Mukhtar, Samal, et al.
Published: (2026)

Cryptanalysis and improvement of multimodal data encryption by machine-learning-based system
by: Tolba, Zakaria
Published: (2024)

Securing RAG: A Risk Assessment and Mitigation Framework
by: Ammann, Lukas, et al.
Published: (2025)

Influence of Parallelism in Vector-Multiplication Units on Correlation Power Analysis
by: Brosch, Manuel, et al.
Published: (2026)

Artificial Intelligence enhanced Security Problems in Real-Time Scenario using Blowfish Algorithm
by: Chinnam, Yuvaraju, et al.
Published: (2024)

Mask-based Membership Inference Attacks for Retrieval-Augmented Generation
by: Liu, Mingrui, et al.
Published: (2024)

RecPS: Privacy Risk Scoring for Recommender Systems
by: He, Jiajie, et al.
Published: (2025)

Membership Inference Attacks on Recommender System: A Survey
by: He, Jiajie, et al.
Published: (2025)

CyberCane: Neuro-Symbolic RAG for Privacy-Preserving Phishing Detection with Formal Ontology Reasoning
by: Hakim, Safayat Bin, et al.
Published: (2026)

PIR-RAG: A System for Private Information Retrieval in Retrieval-Augmented Generation
by: Wang, Baiqiang, et al.
Published: (2025)

Research on the Design of a Short Video Recommendation System Based on Multimodal Information and Differential Privacy
by: Yang, Haowei, et al.
Published: (2025)

SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model
by: Liang, Xun, et al.
Published: (2025)

RAGRank: Using PageRank to Counter Poisoning in CTI LLM Pipelines
by: Jia, Austin, et al.
Published: (2025)

Exposing Privacy Risks in Graph Retrieval-Augmented Generation
by: Liu, Jiale, et al.
Published: (2025)

CryptoAnalystBench: Failures in Multi-Tool Long-Form LLM Analysis
by: Eswaran, Anushri, et al.
Published: (2026)

MAWSEO: Adversarial Wiki Search Poisoning for Illicit Online Promotion
by: Lin, Zilong, et al.
Published: (2023)

A Scenario-Oriented Survey of Federated Recommender Systems: Techniques, Challenges, and Future Directions
by: Mi, Yunqi, et al.
Published: (2025)

Toward Autonomous SOC Operations: End-to-End LLM Framework for Threat Detection, Query Generation, and Resolution in Security Operations
by: Saju, Md Hasan, et al.
Published: (2026)

MoRSE: Bridging the Gap in Cybersecurity Expertise with Retrieval Augmented Generation
by: Simoni, Marco, et al.
Published: (2024)

HijackRAG: Hijacking Attacks against Retrieval-Augmented Large Language Models
by: Zhang, Yucheng, et al.
Published: (2024)

Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an Answer?
by: Shah, Syed Huma
Published: (2026)

User-Side Realization
by: Sato, Ryoma
Published: (2024)

Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation
by: Naseh, Ali, et al.
Published: (2025)

SQuaD: The Software Quality Dataset
by: Robredo, Mikel, et al.
Published: (2025)

Membership Inference Attacks on LLM-based Recommender Systems
by: He, Jiajie, et al.
Published: (2025)

TableGuard -- Securing Structured & Unstructured Data
by: Sharma, Anantha, et al.
Published: (2024)

ChineseHarm-Bench: A Chinese Harmful Content Detection Benchmark
by: Liu, Kangwei, et al.
Published: (2025)

EmojiPrompt: Generative Prompt Obfuscation for Privacy-Preserving Communication with Cloud-based LLMs
by: Lin, Sam, et al.
Published: (2024)