How adversarial attacks can disrupt seemingly stable accurate classifiers
Fuente:
arXiv
Guardado en:
| Autores principales: | Sutton, Oliver J., Zhou, Qinghua, Tyukin, Ivan Y., Gorban, Alexander N., Bastounis, Alexander, Higham, Desmond J. |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
Stealth edits to large language models
por: Sutton, Oliver J., et al.
Publicado: (2024)
por: Sutton, Oliver J., et al.
Publicado: (2024)
The Boundaries of Verifiable Accuracy, Robustness, and Generalisation in Deep Learning
por: Bastounis, Alexander, et al.
Publicado: (2023)
por: Bastounis, Alexander, et al.
Publicado: (2023)
Staining and locking computer vision models without retraining
por: Sutton, Oliver J., et al.
Publicado: (2025)
por: Sutton, Oliver J., et al.
Publicado: (2025)
Weakly Supervised Learners for Correction of AI Errors with Provable Performance Guarantees
por: Tyukin, Ivan Y., et al.
Publicado: (2024)
por: Tyukin, Ivan Y., et al.
Publicado: (2024)
Harnessing non-adversarial robustness in large language models
por: Zhou, Qinghua, et al.
Publicado: (2026)
por: Zhou, Qinghua, et al.
Publicado: (2026)
StepProof: Step-by-step verification of natural language mathematical proofs
por: Hu, Xiaolin, et al.
Publicado: (2025)
por: Hu, Xiaolin, et al.
Publicado: (2025)
The mathematics of adversarial attacks in AI -- Why deep learning is unstable despite the existence of stable neural networks
por: Bastounis, Alexander, et al.
Publicado: (2021)
por: Bastounis, Alexander, et al.
Publicado: (2021)
Embedding Hidden Adversarial Capabilities in Pre-Trained Diffusion Models
por: Beerens, Lucas, et al.
Publicado: (2025)
por: Beerens, Lucas, et al.
Publicado: (2025)
Deceptive Diffusion: Generating Synthetic Adversarial Examples
por: Beerens, Lucas, et al.
Publicado: (2024)
por: Beerens, Lucas, et al.
Publicado: (2024)
Deterministic versus stochastic dynamical classifiers: opposing random adversarial attacks with noise
por: Chicchi, Lorenzo, et al.
Publicado: (2024)
por: Chicchi, Lorenzo, et al.
Publicado: (2024)
Are We Measuring Oversmoothing in Graph Neural Networks Correctly?
por: Zhang, Kaicheng, et al.
Publicado: (2025)
por: Zhang, Kaicheng, et al.
Publicado: (2025)
Enhancing Inference Efficiency of Large Language Models: Investigating Optimization Strategies and Architectural Innovations
por: Tyukin, Georgy
Publicado: (2024)
por: Tyukin, Georgy
Publicado: (2024)
Bias in the Mirror: Are LLMs opinions robust to their own adversarial attacks ?
por: Rennard, Virgile, et al.
Publicado: (2024)
por: Rennard, Virgile, et al.
Publicado: (2024)
Fixed-point graph convolutional networks against adversarial attacks
por: Khan, Shakib, et al.
Publicado: (2025)
por: Khan, Shakib, et al.
Publicado: (2025)
When fractional quasi p-norms concentrate
por: Tyukin, Ivan Y., et al.
Publicado: (2025)
por: Tyukin, Ivan Y., et al.
Publicado: (2025)
Discrete optimal transport is a strong audio adversarial attack
por: Selitskiy, Anton, et al.
Publicado: (2025)
por: Selitskiy, Anton, et al.
Publicado: (2025)
Effective faking of verbal deception detection with target-aligned adversarial attacks
por: Kleinberg, Bennett, et al.
Publicado: (2025)
por: Kleinberg, Bennett, et al.
Publicado: (2025)
Deep generative models as an adversarial attack strategy for tabular machine learning
por: Dyrmishi, Salijona, et al.
Publicado: (2024)
por: Dyrmishi, Salijona, et al.
Publicado: (2024)
Properties that allow or prohibit transferability of adversarial attacks among quantized networks
por: Shrestha, Abhishek, et al.
Publicado: (2024)
por: Shrestha, Abhishek, et al.
Publicado: (2024)
Empirical evaluation of the Frank-Wolfe methods for constructing white-box adversarial attacks
por: Korotkova, Kristina, et al.
Publicado: (2025)
por: Korotkova, Kristina, et al.
Publicado: (2025)
Can adversarial attacks by large language models be attributed?
por: Cebrian, Manuel, et al.
Publicado: (2024)
por: Cebrian, Manuel, et al.
Publicado: (2024)
Multi-style conversion for semantic segmentation of lesions in fundus images by adversarial attacks
por: Playout, Clément, et al.
Publicado: (2024)
por: Playout, Clément, et al.
Publicado: (2024)
Krum Federated Chain (KFC): Using blockchain to defend against adversarial attacks in Federated Learning
por: García-Márquez, Mario, et al.
Publicado: (2025)
por: García-Márquez, Mario, et al.
Publicado: (2025)
GPT-ology, Computational Models, Silicon Sampling: How should we think about LLMs in Cognitive Science?
por: Ong, Desmond C.
Publicado: (2024)
por: Ong, Desmond C.
Publicado: (2024)
FRAUD-RLA: A new reinforcement learning adversarial attack against credit card fraud detection
por: Lunghi, Daniele, et al.
Publicado: (2025)
por: Lunghi, Daniele, et al.
Publicado: (2025)
Problem space structural adversarial attacks for Network Intrusion Detection Systems based on Graph Neural Networks
por: Venturi, Andrea, et al.
Publicado: (2024)
por: Venturi, Andrea, et al.
Publicado: (2024)
On the consistent reasoning paradox of intelligence and optimal trust in AI: The power of 'I don't know'
por: Bastounis, Alexander, et al.
Publicado: (2024)
por: Bastounis, Alexander, et al.
Publicado: (2024)
Cross-site scripting adversarial attacks based on deep reinforcement learning: Evaluation and extension study
por: Pasini, Samuele, et al.
Publicado: (2025)
por: Pasini, Samuele, et al.
Publicado: (2025)
Unveiling the optimization process of Physics Informed Neural Networks: How accurate and competitive can PINNs be?
por: Urbán, Jorge F., et al.
Publicado: (2024)
por: Urbán, Jorge F., et al.
Publicado: (2024)
Can an AI-Powered Presentation Platform Based On The Game "Just a Minute" Be Used To Improve Students' Public Speaking Skills?
por: Higham, Frederic, et al.
Publicado: (2025)
por: Higham, Frederic, et al.
Publicado: (2025)
Analysis of the vulnerability of machine learning regression models to adversarial attacks using data from 5G wireless networks
por: Legashev, Leonid, et al.
Publicado: (2025)
por: Legashev, Leonid, et al.
Publicado: (2025)
The Neuromorphic Supremacy
por: Tsybina, Yuliya, et al.
Publicado: (2026)
por: Tsybina, Yuliya, et al.
Publicado: (2026)
PBCAT: Patch-based composite adversarial training against physically realizable attacks on object detection
por: Li, Xiao, et al.
Publicado: (2025)
por: Li, Xiao, et al.
Publicado: (2025)
Accuracy of TextFooler black box adversarial attacks on 01 loss sign activation neural network ensemble
por: Xue, Yunzhe, et al.
Publicado: (2024)
por: Xue, Yunzhe, et al.
Publicado: (2024)
RAB$^2$-DEF: Dynamic and explainable defense against adversarial attacks in Federated Learning to fair poor clients
por: Rodríguez-Barroso, Nuria, et al.
Publicado: (2024)
por: Rodríguez-Barroso, Nuria, et al.
Publicado: (2024)
To what extent can ASV systems naturally defend against spoofing attacks?
por: Jung, Jee-weon, et al.
Publicado: (2024)
por: Jung, Jee-weon, et al.
Publicado: (2024)
A robust three-way classifier with shadowed granular-balls based on justifiable granularity
por: Yang, Jie, et al.
Publicado: (2024)
por: Yang, Jie, et al.
Publicado: (2024)
Vision Transformers: the threat of realistic adversarial patches
por: Cools, Kasper, et al.
Publicado: (2025)
por: Cools, Kasper, et al.
Publicado: (2025)
Trainwreck: A damaging adversarial attack on image classifiers
por: Zahálka, Jan
Publicado: (2023)
por: Zahálka, Jan
Publicado: (2023)
What is Hiding in Medicine's Dark Matter? Learning with Missing Data in Medical Practices
por: Suzen, Neslihan, et al.
Publicado: (2024)
por: Suzen, Neslihan, et al.
Publicado: (2024)
Ejemplares similares
-
Stealth edits to large language models
por: Sutton, Oliver J., et al.
Publicado: (2024) -
The Boundaries of Verifiable Accuracy, Robustness, and Generalisation in Deep Learning
por: Bastounis, Alexander, et al.
Publicado: (2023) -
Staining and locking computer vision models without retraining
por: Sutton, Oliver J., et al.
Publicado: (2025) -
Weakly Supervised Learners for Correction of AI Errors with Provable Performance Guarantees
por: Tyukin, Ivan Y., et al.
Publicado: (2024) -
Harnessing non-adversarial robustness in large language models
por: Zhou, Qinghua, et al.
Publicado: (2026)