Copertina

Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Haowei, Zhang, Rupeng, Wang, Junjie, Li, Mingyang, Huang, Yuekai, Wang, Dandan, Wang, Qing
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Cryptography and Security Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection
di: Wang, Haowei, et al.
Pubblicazione: (2024)

One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems
di: Chang, Zhiyuan, et al.
Pubblicazione: (2025)

AdInject: Real-World Black-Box Attacks on Web Agents via Advertising Delivery
di: Wang, Haowei, et al.
Pubblicazione: (2025)

Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System
di: Jiang, Ziyou, et al.
Pubblicazione: (2025)

PIDP-Attack: Combining Prompt Injection with Database Poisoning Attacks on Retrieval-Augmented Generation Systems
di: Wang, Haozhen, et al.
Pubblicazione: (2026)

Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation
di: Yang, Peiru, et al.
Pubblicazione: (2026)

Fall into a Pit, Gain in a Wit: Cognitive-Guided Harmful Meme Detection via Misjudgment Risk Pattern Retrieval
di: Wang, Wenshuo, et al.
Pubblicazione: (2025)

Hidden in the Metadata: Stealth Poisoning Attacks on Multimodal Retrieval-Augmented Generation
di: Edemacu, Kennedy, et al.
Pubblicazione: (2026)

Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning
di: Chang, Zhiyuan, et al.
Pubblicazione: (2026)

Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks?
di: Mu, Junjie, et al.
Pubblicazione: (2025)

RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis
di: Tan, Xue, et al.
Pubblicazione: (2024)

KEPo: Knowledge Evolution Poison on Graph-based Retrieval-Augmented Generation
di: Chen, Qizhi, et al.
Pubblicazione: (2026)

Generating Is Believing: Membership Inference Attacks against Retrieval-Augmented Generation
di: Li, Yuying, et al.
Pubblicazione: (2024)

Adversarial Hubness Detector: Detecting Hubness Poisoning in Retrieval-Augmented Generation Systems
di: Habler, Idan, et al.
Pubblicazione: (2026)

CBPF: Filtering Poisoned Data Based on Composite Backdoor Attack
di: Xia, Hanfeng, et al.
Pubblicazione: (2024)

LoopTrap: Termination Poisoning Attacks on LLM Agents
di: Xu, Huiyu, et al.
Pubblicazione: (2026)

PR-Attack: Coordinated Prompt-RAG Attacks on Retrieval-Augmented Generation in Large Language Models via Bilevel Optimization
di: Jiao, Yang, et al.
Pubblicazione: (2025)

Human-Imperceptible Retrieval Poisoning Attacks in LLM-Powered Applications
di: Zhang, Quan, et al.
Pubblicazione: (2024)

Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directions
di: Xu, Yuming, et al.
Pubblicazione: (2026)

Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues
di: Chang, Zhiyuan, et al.
Pubblicazione: (2024)

Beyond Explicit Refusals: Soft-Failure Attacks on Retrieval-Augmented Generation
di: Zhang, Wentao, et al.
Pubblicazione: (2026)

The Resurgence of GCG Adversarial Attacks on Large Language Models
di: Tan, Yuting, et al.
Pubblicazione: (2025)

Checkpoint-GCG: Auditing and Attacking Fine-Tuning-Based Prompt Injection Defenses
di: Yang, Xiaoxue, et al.
Pubblicazione: (2025)

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

Reasoning-Style Poisoning of LLM Agents via Stealthy Style Transfer: Process-Level Attacks and Runtime Monitoring in RSV Space
di: Zhou, Xingfu, et al.
Pubblicazione: (2025)

Turning Generative Models Degenerate: The Power of Data Poisoning Attacks
di: Jiang, Shuli, et al.
Pubblicazione: (2024)

WHITE PAPER: A Brief Exploration of Data Exfiltration using GCG Suffixes
di: Valbuena, Victor
Pubblicazione: (2024)

RAG-WM: An Efficient Black-Box Watermarking Approach for Retrieval-Augmented Generation of Large Language Models
di: Lv, Peizhuo, et al.
Pubblicazione: (2025)

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

Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models
di: Shan, Shawn, et al.
Pubblicazione: (2023)

Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning Attacks
di: Cotroneo, Domenico, et al.
Pubblicazione: (2023)

Medusa: Cross-Modal Transferable Adversarial Attacks on Multimodal Medical Retrieval-Augmented Generation
di: Shang, Yingjia, et al.
Pubblicazione: (2025)

Do Multimodal RAG Systems Leak Data? A Comprehensive Evaluation of Membership Inference and Image Caption Retrieval Attacks
di: Al-Lawati, Ali, et al.
Pubblicazione: (2026)

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

Exploring the Vulnerabilities of Federated Learning: A Deep Dive into Gradient Inversion Attacks
di: Guo, Pengxin, et al.
Pubblicazione: (2025)

Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents
di: Zou, Wei, et al.
Pubblicazione: (2026)

Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models
di: Li, Xiao, et al.
Pubblicazione: (2024)

Differentially Private Retrieval-Augmented Generation
di: Tang, Tingting, et al.
Pubblicazione: (2026)

CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent
di: Ning, Liang-bo, et al.
Pubblicazione: (2025)

System Prompt Poisoning: Persistent Attacks on Large Language Models Beyond User Injection
di: Li, Zongze, et al.
Pubblicazione: (2025)