Buchumschlag

Query Provenance Analysis: Efficient and Robust Defense against Query-based Black-box Attacks

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Li, Shaofei, Zhang, Ziqi, Jia, Haomin, Li, Ding, Guo, Yao, Chen, Xiangqun
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Cryptography and Security
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Multi-task Adversarial Attacks against Black-box Model with Few-shot Queries
von: Wang, Wenqiang, et al.
Veröffentlicht: (2025)

PuriDefense: Randomized Local Implicit Adversarial Purification for Defending Black-box Query-based Attacks
von: Guo, Ping, et al.
Veröffentlicht: (2024)

Connect the Dots: Knowledge Graph-Guided Crawler Attack on Retrieval-Augmented Generation Systems
von: Yao, Mengyu, et al.
Veröffentlicht: (2026)

SEA: Shareable and Explainable Attribution for Query-based Black-box Attacks
von: Gao, Yue, et al.
Veröffentlicht: (2023)

Moss: Proxy Model-based Full-Weight Aggregation in Federated Learning with Heterogeneous Models
von: Cai, Yifeng, et al.
Veröffentlicht: (2025)

MIRAGE: Misleading Retrieval-Augmented Generation via Black-box and Query-agnostic Poisoning Attacks
von: Chen, Tailun, et al.
Veröffentlicht: (2025)

ICL-EVADER: Zero-Query Black-Box Evasion Attacks on In-Context Learning and Their Defenses
von: He, Ningyuan, et al.
Veröffentlicht: (2026)

Mind the Gap: Detecting Black-box Adversarial Attacks in the Making through Query Update Analysis
von: Park, Jeonghwan, et al.
Veröffentlicht: (2025)

PromoGuardian: Detecting Promotion Abuse Fraud with Multi-Relation Fused Graph Neural Networks
von: Li, Shaofei, et al.
Veröffentlicht: (2025)

No Data? No Problem: Synthesizing Security Graphs for Better Intrusion Detection
von: Huang, Yi, et al.
Veröffentlicht: (2025)

ProGQL: A Provenance Graph Query System for Cyber Attack Investigation
von: Shao, Fei, et al.
Veröffentlicht: (2025)

Zero-Query Adversarial Attack on Black-box Automatic Speech Recognition Systems
von: Fang, Zheng, et al.
Veröffentlicht: (2024)

KnowHow: Automatically Applying High-Level CTI Knowledge for Interpretable and Accurate Provenance Analysis
von: Meng, Yuhan, et al.
Veröffentlicht: (2025)

Marlin: Knowledge-Driven Analysis of Provenance Graphs for Efficient and Robust Detection of Cyber Attacks
von: Li, Zhenyuan, et al.
Veröffentlicht: (2024)

RL-JACK: Reinforcement Learning-powered Black-box Jailbreaking Attack against LLMs
von: Chen, Xuan, et al.
Veröffentlicht: (2024)

Bones of Contention: Exploring Query-Efficient Attacks against Skeleton Recognition Systems
von: Cao, Yuxin, et al.
Veröffentlicht: (2025)

Dashed Line Defense: Plug-And-Play Defense Against Adaptive Score-Based Query Attacks
von: Fu, Yanzhang, et al.
Veröffentlicht: (2026)

KG-DF: A Black-box Defense Framework against Jailbreak Attacks Based on Knowledge Graphs
von: Liu, Shuyuan, et al.
Veröffentlicht: (2025)

"Someone Hid It": Query-Agnostic Black-Box Attacks on LLM-Based Retrieval
von: Li, Jiate, et al.
Veröffentlicht: (2026)

Query Recovery from Easy to Hard: Jigsaw Attack against SSE
von: Nie, Hao, et al.
Veröffentlicht: (2024)

Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks
von: Xiong, Chen, et al.
Veröffentlicht: (2024)

TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models
von: Li, Ding, et al.
Veröffentlicht: (2024)

Five Queries Are Enough: Query-Efficient and Surrogate-Free Membership Inference Attacks on RAG via Entailment
von: Nguyen, Nguyen Linh Bao, et al.
Veröffentlicht: (2026)

Q-FAKER: Query-free Hard Black-box Attack via Controlled Generation
von: Na, CheolWon, et al.
Veröffentlicht: (2025)

Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
von: Yi, Biao, et al.
Veröffentlicht: (2025)

Black-box Membership Inference Attacks against Fine-tuned Diffusion Models
von: Pang, Yan, et al.
Veröffentlicht: (2023)

MirGuard: Towards a Robust Provenance-based Intrusion Detection System Against Graph Manipulation Attacks
von: Sang, Anyuan, et al.
Veröffentlicht: (2025)

I Can Tell Your Secrets: Inferring Privacy Attributes from Mini-app Interaction History in Super-apps
von: Cai, Yifeng, et al.
Veröffentlicht: (2025)

From Head to Tail: Efficient Black-box Model Inversion Attack via Long-tailed Learning
von: Li, Ziang, et al.
Veröffentlicht: (2025)

BruSLeAttack: A Query-Efficient Score-Based Black-Box Sparse Adversarial Attack
von: Vo, Viet Quoc, et al.
Veröffentlicht: (2024)

Latent Geometric Chords for Query-Efficient Decision-Based Adversarial Attacks
von: Khine, Ei Hmue, et al.
Veröffentlicht: (2026)

Rotated Robustness: A Training-Free Defense against Bit-Flip Attacks on Large Language Models
von: Liu, Deng, et al.
Veröffentlicht: (2026)

DeMark: A Query-Free Black-Box Attack on Deepfake Watermarking Defenses
von: Song, Wei, et al.
Veröffentlicht: (2026)

AgentTypo: Adaptive Typographic Prompt Injection Attacks against Black-box Multimodal Agents
von: Li, Yanjie, et al.
Veröffentlicht: (2025)

White-box Membership Inference Attacks against Diffusion Models
von: Pang, Yan, et al.
Veröffentlicht: (2023)

Multi-granular Adversarial Attacks against Black-box Neural Ranking Models
von: Liu, Yu-An, et al.
Veröffentlicht: (2024)

QUEEN: Query Unlearning against Model Extraction
von: Chen, Huajie, et al.
Veröffentlicht: (2024)

Pop Quiz Attack: Black-box Membership Inference Attacks Against Large Language Models
von: Chen, Zeyuan, et al.
Veröffentlicht: (2026)

FBA$^2$D: Frequency-based Black-box Attack for AI-generated Image Detection
von: Chen, Xiaojing, et al.
Veröffentlicht: (2025)

Bounding-box Watermarking: Defense against Model Extraction Attacks on Object Detectors
von: Koda, Satoru, et al.
Veröffentlicht: (2024)