Buchumschlag

Accuracy of TextFooler black box adversarial attacks on 01 loss sign activation neural network ensemble

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Xue, Yunzhe, Roshan, Usman
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Machine Learning Artificial Intelligence Cryptography and Security
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Are aligned neural networks adversarially aligned?
von: Carlini, Nicholas, et al.
Veröffentlicht: (2023)

Effective backdoor attack on graph neural networks in link prediction tasks
von: Dai, Jiazhu, et al.
Veröffentlicht: (2024)

Enhancing web traffic attacks identification through ensemble methods and feature selection
von: Urda, Daniel, et al.
Veröffentlicht: (2024)

RAB$^2$-DEF: Dynamic and explainable defense against adversarial attacks in Federated Learning to fair poor clients
von: Rodríguez-Barroso, Nuria, et al.
Veröffentlicht: (2024)

ThinkTrap: Denial-of-Service Attacks against Black-box LLM Services via Infinite Thinking
von: Li, Yunzhe, et al.
Veröffentlicht: (2025)

AED: An black-box NLP classifier model attacker
von: Liu, Yueyang, et al.
Veröffentlicht: (2021)

Sparsity in neural networks can improve their privacy
von: Gonon, Antoine, et al.
Veröffentlicht: (2023)

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

AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses
von: Carlini, Nicholas, et al.
Veröffentlicht: (2025)

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

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

Machine Learning needs Better Randomness Standards: Randomised Smoothing and PRNG-based attacks
von: Dahiya, Pranav, et al.
Veröffentlicht: (2023)

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

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

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

An Investigation into the Performances of the State-of-the-art Machine Learning Approaches for Various Cyber-attack Detection: A Survey
von: Ige, Tosin, et al.
Veröffentlicht: (2024)

Analysis of the vulnerability of machine learning regression models to adversarial attacks using data from 5G wireless networks
von: Legashev, Leonid, et al.
Veröffentlicht: (2025)

Defense effectiveness across architectural layers: a mechanistic evaluation of persistent memory attacks on stateful LLM agents
von: Leong, Jun Wen
Veröffentlicht: (2026)

Reconstruction of Differentially Private Text Sanitization via Large Language Models
von: Pang, Shuchao, et al.
Veröffentlicht: (2024)

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

Black-box Adversarial Attacks on Network-wide Multi-step Traffic State Prediction Models
von: Poudel, Bibek, et al.
Veröffentlicht: (2021)

PRO: Enabling Precise and Robust Text Watermark for Open-Source LLMs
von: Xue, Jiaqi, et al.
Veröffentlicht: (2025)

Nonideality-aware training makes memristive networks more robust to adversarial attacks
von: Joksas, Dovydas, et al.
Veröffentlicht: (2024)

Privacy and Accuracy Implications of Model Complexity and Integration in Heterogeneous Federated Learning
von: Németh, Gergely Dániel, et al.
Veröffentlicht: (2023)

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

Improving Clean Accuracy via a Tangent-Space Perspective on Adversarial Training
von: Yi, Bongsoo, et al.
Veröffentlicht: (2024)

Disrupting Model Merging: A Parameter-Level Defense Without Sacrificing Accuracy
von: Junhao, Wei, et al.
Veröffentlicht: (2025)

Accuracy-Privacy Trade-off in the Mitigation of Membership Inference Attack in Federated Learning
von: Ahamed, Sayyed Farid, et al.
Veröffentlicht: (2024)

Advancing Recommender Systems by mitigating Shilling attacks
von: Chichani, Aditya, et al.
Veröffentlicht: (2024)

Power side-channel leakage localization through adversarial training of deep neural networks
von: Gammell, Jimmy, et al.
Veröffentlicht: (2024)

Learning to Forget using Hypernetworks
von: Rangel, Jose Miguel Lara, et al.
Veröffentlicht: (2024)

Bayes' capacity as a measure for reconstruction attacks in federated learning
von: Biswas, Sayan, et al.
Veröffentlicht: (2024)

Blending adversarial training and representation-conditional purification via aggregation improves adversarial robustness
von: Ballarin, Emanuele, et al.
Veröffentlicht: (2023)

Problem space structural adversarial attacks for Network Intrusion Detection Systems based on Graph Neural Networks
von: Venturi, Andrea, et al.
Veröffentlicht: (2024)

Recalling The Forgotten Class Memberships: Unlearned Models Can Be Noisy Labelers to Leak Privacy
von: Sui, Zhihao, et al.
Veröffentlicht: (2025)

Evaluating Differentially Private Generation of Domain-Specific Text
von: Sun, Yidan, et al.
Veröffentlicht: (2025)

The last Dance : Robust backdoor attack via diffusion models and bayesian approach
von: Mengara, Orson
Veröffentlicht: (2024)

Learning to Watermark LLM-generated Text via Reinforcement Learning
von: Xu, Xiaojun, et al.
Veröffentlicht: (2024)

AuthorMist: Evading AI Text Detectors with Reinforcement Learning
von: David, Isaac, et al.
Veröffentlicht: (2025)

Exploiting Class Probabilities for Black-box Sentence-level Attacks
von: Moraffah, Raha, et al.
Veröffentlicht: (2024)