Copertina

AED: An black-box NLP classifier model attacker

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liu, Yueyang, Huang, Yan, Cai, Zhipeng
Natura:	Preprint
Pubblicazione:	2021
Soggetti:	Machine Learning Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Embedding-based classifiers can detect prompt injection attacks
di: Ayub, Md. Ahsan, et al.
Pubblicazione: (2024)

Accuracy of TextFooler black box adversarial attacks on 01 loss sign activation neural network ensemble
di: Xue, Yunzhe, et al.
Pubblicazione: (2024)

Trainwreck: A damaging adversarial attack on image classifiers
di: Zahálka, Jan
Pubblicazione: (2023)

Correlation inference attacks against machine learning models
di: Creţu, Ana-Maria, et al.
Pubblicazione: (2021)

AED: Automatic Discovery of Effective and Diverse Vulnerabilities for Autonomous Driving Policy with Large Language Models
di: Qiu, Le, et al.
Pubblicazione: (2025)

BLIA: Detect model memorization in binary classification model through passive Label Inference attack
di: Khan, Mohammad Wahiduzzaman, et al.
Pubblicazione: (2025)

A hierarchical approach for assessing the vulnerability of tree-based classification models to membership inference attack
di: Preen, Richard J., et al.
Pubblicazione: (2025)

Black-box Optimization of LLM Outputs by Asking for Directions
di: Zhang, Jie, et al.
Pubblicazione: (2025)

SHLIME: Foiling adversarial attacks fooling SHAP and LIME
di: Chauhan, Sam, et al.
Pubblicazione: (2025)

A novel reliability attack of Physical Unclonable Functions
di: Li, Gaoxiang, et al.
Pubblicazione: (2024)

Noisy Neighbors: Efficient membership inference attacks against LLMs
di: Galli, Filippo, et al.
Pubblicazione: (2024)

Evaluating lightweight unsupervised online IDS for masquerade attacks in CAN
di: Moriano, Pablo, et al.
Pubblicazione: (2024)

Malware Classification Leveraging NLP & Machine Learning for Enhanced Accuracy
di: Gond, Bishwajit Prasad, et al.
Pubblicazione: (2025)

Traceable Black-box Watermarks for Federated Learning
di: Xu, Jiahao, et al.
Pubblicazione: (2025)

AED-PADA:Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptation
di: Peng, Heqi, et al.
Pubblicazione: (2024)

Evading Black-box Classifiers Without Breaking Eggs
di: Debenedetti, Edoardo, et al.
Pubblicazione: (2023)

A clean-label graph backdoor attack method in node classification task
di: Xing, Xiaogang, et al.
Pubblicazione: (2023)

Virtual camera detection: Catching video injection attacks in remote biometric systems
di: Kurmankhojayev, Daniyar, et al.
Pubblicazione: (2025)

AlertBERT: A noise-robust alert grouping framework for simultaneous cyber attacks
di: Karner, Lukas, et al.
Pubblicazione: (2026)

Investigating the Effect of Misalignment on Membership Privacy in the White-box Setting
di: Cretu, Ana-Maria, et al.
Pubblicazione: (2023)

Black-box Adversarial Transferability: An Empirical Study in Cybersecurity Perspective
di: Roshan, Khushnaseeb, et al.
Pubblicazione: (2024)

Dynamic Black-box Backdoor Attacks on IoT Sensory Data
di: Chathoth, Ajesh Koyatan, et al.
Pubblicazione: (2025)

Towards the generation of hierarchical attack models from cybersecurity vulnerabilities using language models
di: Sowka, Kacper, et al.
Pubblicazione: (2024)

Exploring the limits of strong membership inference attacks on large language models
di: Hayes, Jamie, et al.
Pubblicazione: (2025)

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

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs
di: Lv, Peizhuo, et al.
Pubblicazione: (2025)

Anticipated Network Surveillance -- An extrapolated study to predict cyber-attacks using Machine Learning and Data Analytics
di: Srivastava, Aviral, et al.
Pubblicazione: (2023)

Online Poisoning Attack Against Reinforcement Learning under Black-box Environments
di: Li, Jianhui, et al.
Pubblicazione: (2024)

I can't see it but I can Fine-tune it: On Encrypted Fine-tuning of Transformers using Fully Homomorphic Encryption
di: Panzade, Prajwal, et al.
Pubblicazione: (2024)

New intelligent defense systems to reduce the risks of Selfish Mining and Double-Spending attacks using Learning Automata
di: Ghoreishi, Seyed Ardalan, et al.
Pubblicazione: (2023)

Learning diverse attacks on large language models for robust red-teaming and safety tuning
di: Lee, Seanie, et al.
Pubblicazione: (2024)

EvadeDroid: A Practical Evasion Attack on Machine Learning for Black-box Android Malware Detection
di: Bostani, Hamid, et al.
Pubblicazione: (2021)

MergePrint: Merge-Resistant Fingerprints for Robust Black-box Ownership Verification of Large Language Models
di: Yamabe, Shojiro, et al.
Pubblicazione: (2024)

A Generative Approach to Surrogate-based Black-box Attacks
di: Moraffah, Raha, et al.
Pubblicazione: (2024)

FreeTalk:A plug-and-play and black-box defense against speech synthesis attacks
di: Pu, Yuwen, et al.
Pubblicazione: (2025)

Practicable Black-box Evasion Attacks on Link Prediction in Dynamic Graphs -- A Graph Sequential Embedding Method
di: Li, Jiate, et al.
Pubblicazione: (2024)

Designing an attack-defense game: how to increase robustness of financial transaction models via a competition
di: Zaytsev, Alexey, et al.
Pubblicazione: (2023)

Information Leakage from Embedding in Large Language Models
di: Wan, Zhipeng, et al.
Pubblicazione: (2024)

MF-CLIP: Leveraging CLIP as Surrogate Models for No-box Adversarial Attacks
di: Zhang, Jiaming, et al.
Pubblicazione: (2023)

On the use of neurosymbolic AI for defending against cyber attacks
di: Grov, Gudmund, et al.
Pubblicazione: (2024)