Image de couverture de livre

"Someone Hid It": Query-Agnostic Black-Box Attacks on LLM-Based Retrieval

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Jiate, Cao, Defu, Li, Li, Yang, Wei, Qin, Yuehan, Yu, Chenxiao, Yang, Tiannuo, Rossi, Ryan A., Liu, Yan, Hu, Xiyang, Zhao, Yue
Format:	Preprint
Publié:	2026
Sujets:	Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Practicable Black-box Evasion Attacks on Link Prediction in Dynamic Graphs -- A Graph Sequential Embedding Method
par: Li, Jiate, et autres
Publié: (2024)

MIRAGE: Misleading Retrieval-Augmented Generation via Black-box and Query-agnostic Poisoning Attacks
par: Chen, Tailun, et autres
Publié: (2025)

AGNNCert: Defending Graph Neural Networks against Arbitrary Perturbations with Deterministic Certification
par: Li, Jiate, et autres
Publié: (2025)

No Attacker Needed: Unintentional Cross-User Contamination in Shared-State LLM Agents
par: Yang, Tiankai, et autres
Publié: (2026)

Black-Box Skill Stealing Attack from Proprietary LLM Agents: An Empirical Study
par: Wang, Zihan, et autres
Publié: (2026)

Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks
par: Li, Jiate, et autres
Publié: (2025)

ICL-EVADER: Zero-Query Black-Box Evasion Attacks on In-Context Learning and Their Defenses
par: He, Ningyuan, et autres
Publié: (2026)

Query Provenance Analysis: Efficient and Robust Defense against Query-based Black-box Attacks
par: Li, Shaofei, et autres
Publié: (2024)

Deterministic Certification of Graph Neural Networks against Graph Poisoning Attacks with Arbitrary Perturbations
par: Li, Jiate, et autres
Publié: (2025)

Can Drift-Adaptive Malware Detectors Be Made Robust? Attacks and Defenses Under White-Box and Black-Box Threats
par: Li, Adrian Shuai, et autres
Publié: (2026)

PolyJailbreak: Cross-Modal Jailbreaking Attacks on Black-Box Multimodal LLMs
par: Wang, Xinkai, et autres
Publié: (2025)

Benchmarking Knowledge-Extraction Attack and Defense on Retrieval-Augmented Generation
par: Qi, Zhisheng, et autres
Publié: (2026)

BruSLeAttack: A Query-Efficient Score-Based Black-Box Sparse Adversarial Attack
par: Vo, Viet Quoc, et autres
Publié: (2024)

SLIM: Stealthy Low-Coverage Black-Box Watermarking via Latent-Space Confusion Zones
par: Wu, Hengyu, et autres
Publié: (2026)

SemiAdv: Query-Efficient Black-Box Adversarial Attack with Unlabeled Images
par: Fan, Mingyuan, et autres
Publié: (2024)

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

Enhanced MLLM Black-Box Jailbreaking Attacks and Defenses
par: Zhong, Xingwei, et autres
Publié: (2025)

Knock-Knock: Black-Box, Platform-Agnostic DRAM Address-Mapping Reverse Engineering
par: Plin, Antoine, et autres
Publié: (2025)

Tricking Retrievers with Influential Tokens: An Efficient Black-Box Corpus Poisoning Attack
par: Wang, Cheng, et autres
Publié: (2025)

Rethinking LLM Watermark Detection in Black-Box Settings: A Non-Intrusive Third-Party Framework
par: Wang, Zhuoshang, et autres
Publié: (2026)

Black-Box Membership Inference Attack for LVLMs via Prior Knowledge-Calibrated Memory Probing
par: Yin, Jinhua, et autres
Publié: (2025)

Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning
par: Domico, Kyle, et autres
Publié: (2025)

Defenses Against Prompt Attacks Learn Surface Heuristics
par: Li, Shawn, et autres
Publié: (2026)

AdInject: Real-World Black-Box Attacks on Web Agents via Advertising Delivery
par: Wang, Haowei, et autres
Publié: (2025)

Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolution
par: Zhang, Xiaozhe, et autres
Publié: (2026)

SEA: Shareable and Explainable Attribution for Query-based Black-box Attacks
par: Gao, Yue, et autres
Publié: (2023)

A Hard-Label Black-Box Evasion Attack against ML-based Malicious Traffic Detection Systems
par: Liu, Zixuan, et autres
Publié: (2025)

Transferable & Stealthy Ensemble Attacks: A Black-Box Jailbreaking Framework for Large Language Models
par: Yang, Yiqi, et autres
Publié: (2024)

ComMark: Covert and Robust Black-Box Model Watermarking with Compressed Samples
par: Yang, Yunfei, et autres
Publié: (2025)

GRAPHTEXTACK: A Realistic Black-Box Node Injection Attack on LLM-Enhanced GNNs
par: Ma, Jiaji, et autres
Publié: (2025)

Black-Box Guardrail Reverse-engineering Attack
par: Yao, Hongwei, et autres
Publié: (2025)

External Data Extraction Attacks against Retrieval-Augmented Large Language Models
par: He, Yu, et autres
Publié: (2025)

StruPhantom: Evolutionary Injection Attacks on Black-Box Tabular Agents Powered by Large Language Models
par: Feng, Yang, et autres
Publié: (2025)

The RAG Paradox: A Black-Box Attack Exploiting Unintentional Vulnerabilities in Retrieval-Augmented Generation Systems
par: Choi, Chanwoo, et autres
Publié: (2025)

FlexLLM: Exploring LLM Customization for Moving Target Defense on Black-Box LLMs Against Jailbreak Attacks
par: Chen, Bocheng, et autres
Publié: (2024)

Generating Is Believing: Membership Inference Attacks against Retrieval-Augmented Generation
par: Li, Yuying, et autres
Publié: (2024)

Fine-Tuning Jailbreaks under Highly Constrained Black-Box Settings: A Three-Pronged Approach
par: Li, Xiangfang, et autres
Publié: (2025)

Invisible Hands: Gray-Box Bit Flip Attack for Steering LLMs Without Knowledge of Gradients, Data, and Weights
par: Almalky, Abeer Matar A., et autres
Publié: (2025)

Discovering New Shadow Patterns for Black-Box Attacks on Lane Detection of Autonomous Vehicles
par: MohajerAnsari, Pedram, et autres
Publié: (2024)

MalTool: Malicious Tool Attacks on LLM Agents
par: Hu, Yuepeng, et autres
Publié: (2026)