GASLITEing the Retrieval: Exploring Vulnerabilities in Dense Embedding-based Search

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ben-Tov, Matan, Sharif, Mahmood
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Cryptography and Security Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Universal Jailbreak Suffixes Are Strong Attention Hijackers
di: Ben-Tov, Matan, et al.
Pubblicazione: (2025)

CaFA: Cost-aware, Feasible Attacks With Database Constraints Against Neural Tabular Classifiers
di: Ben-Tov, Matan, et al.
Pubblicazione: (2025)

Impactful Bit-Flip Search on Full-precision Models
di: Benedek, Nadav, et al.
Pubblicazione: (2024)

Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation
di: Zhang, Jiankun, et al.
Pubblicazione: (2025)

Exploring Backdoor Vulnerabilities of Chat Models
di: Hao, Yunzhuo, et al.
Pubblicazione: (2024)

RAG Safety: Exploring Knowledge Poisoning Attacks to Retrieval-Augmented Generation
di: Zhao, Tianzhe, et al.
Pubblicazione: (2025)

WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation Watermarks
di: Shetty, Anudeex, et al.
Pubblicazione: (2024)

Exploring Vulnerabilities and Protections in Large Language Models: A Survey
di: Liu, Frank Weizhen, et al.
Pubblicazione: (2024)

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface
di: Labunets, Andrey, et al.
Pubblicazione: (2025)

A First Look at GPT Apps: Landscape and Vulnerability
di: Zhang, Zejun, et al.
Pubblicazione: (2024)

Relevance as a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents
di: Nawal, Aditya, et al.
Pubblicazione: (2026)

The Double-edged Sword of LLM-based Data Reconstruction: Understanding and Mitigating Contextual Vulnerability in Word-level Differential Privacy Text Sanitization
di: Meisenbacher, Stephen, et al.
Pubblicazione: (2025)

Are My Optimized Prompts Compromised? Exploring Vulnerabilities of LLM-based Optimizers
di: Zhao, Andrew, et al.
Pubblicazione: (2025)

ChatNVD: Advancing Cybersecurity Vulnerability Assessment with Large Language Models
di: Chopra, Shivansh, et al.
Pubblicazione: (2024)

RealVul: Can We Detect Vulnerabilities in Web Applications with LLM?
di: Cao, Di, et al.
Pubblicazione: (2024)

ExtremeAIGC: Benchmarking LMM Vulnerability to AI-Generated Extremist Content
di: Chandna, Bhavik, et al.
Pubblicazione: (2025)

A Character-based Diffusion Embedding Algorithm for Enhancing the Generation Quality of Generative Linguistic Steganographic Texts
di: Chen, Yingquan, et al.
Pubblicazione: (2025)

HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application Vulnerabilities
di: Ren, Xiaoxue, et al.
Pubblicazione: (2025)

Disabling Self-Correction in Retrieval-Augmented Generation via Stealthy Retriever Poisoning
di: Dai, Yanbo, et al.
Pubblicazione: (2025)

CVE-LLM : Ontology-Assisted Automatic Vulnerability Evaluation Using Large Language Models
di: Ghosh, Rikhiya, et al.
Pubblicazione: (2025)

Overlooked Safety Vulnerability in LLMs: Malicious Intelligent Optimization Algorithm Request and its Jailbreak
di: Gu, Haoran, et al.
Pubblicazione: (2026)

Universal Zero-shot Embedding Inversion
di: Zhang, Collin, et al.
Pubblicazione: (2025)

Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs
di: Pathade, Chetan
Pubblicazione: (2025)

What Really Matters in Many-Shot Attacks? An Empirical Study of Long-Context Vulnerabilities in LLMs
di: Kim, Sangyeop, et al.
Pubblicazione: (2025)

Exploring Membership Inference Vulnerabilities in Clinical Large Language Models
di: Nemecek, Alexander, et al.
Pubblicazione: (2025)

Exploring ChatGPT's Capabilities on Vulnerability Management
di: Liu, Peiyu, et al.
Pubblicazione: (2023)

The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)
di: Zeng, Shenglai, et al.
Pubblicazione: (2024)

LibVulnWatch: A Deep Assessment Agent System and Leaderboard for Uncovering Hidden Vulnerabilities in Open-Source AI Libraries
di: Wu, Zekun, et al.
Pubblicazione: (2025)

Block-wise Codeword Embedding for Reliable Multi-bit Text Watermarking
di: Kim, Joeun, et al.
Pubblicazione: (2026)

Geometry-Aware Localized Watermarking for Copyright Protection in Embedding-as-a-Service
di: Chen, Zhimin, et al.
Pubblicazione: (2026)

Data Extraction Attacks in Retrieval-Augmented Generation via Backdoors
di: Peng, Yuefeng, et al.
Pubblicazione: (2024)

Dataset Protection via Watermarked Canaries in Retrieval-Augmented LLMs
di: Liu, Yepeng, et al.
Pubblicazione: (2025)

MultiFuzz: A Dense Retrieval-based Multi-Agent System for Network Protocol Fuzzing
di: Maklad, Youssef, et al.
Pubblicazione: (2025)

SoK: Privacy Risks and Mitigations in Retrieval-Augmented Generation Systems
di: Bodea, Andreea-Elena, et al.
Pubblicazione: (2026)

EmMark: Robust Watermarks for IP Protection of Embedded Quantized Large Language Models
di: Zhang, Ruisi, et al.
Pubblicazione: (2024)

LLMAtKGE: Large Language Models as Explainable Attackers against Knowledge Graph Embeddings
di: Li, Ting, et al.
Pubblicazione: (2025)

How Vulnerable Are Edge LLMs?
di: Ding, Ao, et al.
Pubblicazione: (2026)

Retrieval-Augmented Defense: Adaptive and Controllable Jailbreak Prevention for Large Language Models
di: Yang, Guangyu, et al.
Pubblicazione: (2025)

Behavioral Canaries: Auditing Private Retrieved Context Usage in RL Fine-Tuning
di: Chen, Chaoran, et al.
Pubblicazione: (2026)

Applying Pre-trained Multilingual BERT in Embeddings for Improved Malicious Prompt Injection Attacks Detection
di: Rahman, Md Abdur, et al.
Pubblicazione: (2024)