Buchumschlag

PuriDefense: Randomized Local Implicit Adversarial Purification for Defending Black-box Query-based Attacks

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Guo, Ping, Li, Xiang, Yang, Zhiyuan, Lin, Xi, Zhao, Qingchuan, Zhang, Qingfu
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Cryptography and Security Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

L-AutoDA: Leveraging Large Language Models for Automated Decision-based Adversarial Attacks
von: Guo, Ping, et al.
Veröffentlicht: (2024)

Query Provenance Analysis: Efficient and Robust Defense against Query-based Black-box Attacks
von: Li, Shaofei, et al.
Veröffentlicht: (2024)

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

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

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

Exploring the Adversarial Frontier: Quantifying Robustness via Adversarial Hypervolume
von: Guo, Ping, et al.
Veröffentlicht: (2024)

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

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

BlackboxBench: A Comprehensive Benchmark of Black-box Adversarial Attacks
von: Zheng, Meixi, et al.
Veröffentlicht: (2023)

A Game Between the Defender and the Attacker for Trigger-based Black-box Model Watermarking
von: Huang, Chaoyue, et al.
Veröffentlicht: (2025)

CodePurify: Defend Backdoor Attacks on Neural Code Models via Entropy-based Purification
von: Mu, Fangwen, et al.
Veröffentlicht: (2024)

A Wolf in Sheep's Clothing: Practical Black-box Adversarial Attacks for Evading Learning-based Windows Malware Detection in the Wild
von: Ling, Xiang, et al.
Veröffentlicht: (2024)

Certifiable Black-Box Attacks with Randomized Adversarial Examples: Breaking Defenses with Provable Confidence
von: Hong, Hanbin, et al.
Veröffentlicht: (2023)

AVA: Inconspicuous Attribute Variation-based Adversarial Attack bypassing DeepFake Detection
von: Meng, Xiangtao, et al.
Veröffentlicht: (2023)

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations
von: Zhou, Yihe, et al.
Veröffentlicht: (2025)

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

DNN-Defender: A Victim-Focused In-DRAM Defense Mechanism for Taming Adversarial Weight Attack on DNNs
von: Zhou, Ranyang, et al.
Veröffentlicht: (2023)

MOS-Attack: A Scalable Multi-objective Adversarial Attack Framework
von: Guo, Ping, et al.
Veröffentlicht: (2025)

Privacy-preserving Universal Adversarial Defense for Black-box Models
von: Li, Qiao, et al.
Veröffentlicht: (2024)

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

Black-Box Skill Stealing Attack from Proprietary LLM Agents: An Empirical Study
von: Wang, Zihan, et al.
Veröffentlicht: (2026)

Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs
von: Liu, Fan, et al.
Veröffentlicht: (2024)

When Reasoning Leaks Membership: Membership Inference Attack on Black-box Large Reasoning Models
von: Hu, Ruihan, et al.
Veröffentlicht: (2026)

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

LISArD: Learning Image Similarity to Defend Against Gray-box Adversarial Attacks
von: Costa, Joana C., et al.
Veröffentlicht: (2025)

From Defender to Devil? Unintended Risk Interactions Induced by LLM Defenses
von: Meng, Xiangtao, et al.
Veröffentlicht: (2025)

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

A General Black-box Adversarial Attack on Graph-based Fake News Detectors
von: Zhu, Peican, et al.
Veröffentlicht: (2024)

Defending against Adversarial Malware Attacks on ML-based Android Malware Detection Systems
von: He, Ping, et al.
Veröffentlicht: (2025)

HogVul: Black-box Adversarial Code Generation Framework Against LM-based Vulnerability Detectors
von: Yang, Jingxiao, et al.
Veröffentlicht: (2026)

DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification
von: Kang, Mintong, et al.
Veröffentlicht: (2023)

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

Enhanced MLLM Black-Box Jailbreaking Attacks and Defenses
von: Zhong, Xingwei, et al.
Veröffentlicht: (2025)

Attack as Defense: Run-time Backdoor Implantation for Image Content Protection
von: Zhang, Haichuan, et al.
Veröffentlicht: (2024)

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

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

Defending Against Prompt Injection With a Few DefensiveTokens
von: Chen, Sizhe, et al.
Veröffentlicht: (2025)

DYNAMITE: Dynamic Defense Selection for Enhancing Machine Learning-based Intrusion Detection Against Adversarial Attacks
von: Chen, Jing, et al.
Veröffentlicht: (2025)

RoboJailBench: Benchmarking Adversarial Attacks and Defenses in Embodied Robotic Agents
von: Yeke, Doguhuan, et al.
Veröffentlicht: (2026)

SATversary: Adversarial Attacks and Defenses for Satellite Fingerprinting
von: Smailes, Joshua, et al.
Veröffentlicht: (2025)