Image de couverture de livre

Adversarial Examples Are Not Bugs, They Are Superposition

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gorton, Liv, Lewis, Owen
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Group Crosscoders for Mechanistic Analysis of Symmetry
par: Gorton, Liv
Publié: (2024)

The Missing Curve Detectors of InceptionV1: Applying Sparse Autoencoders to InceptionV1 Early Vision
par: Gorton, Liv
Publié: (2024)

Measuring the Representational Alignment of Neural Systems in Superposition
par: Liu, Sunny, et autres
Publié: (2026)

Understanding sparse autoencoder scaling in the presence of feature manifolds
par: Michaud, Eric J., et autres
Publié: (2025)

Detecting Adversarial Examples
par: Mumcu, Furkan, et autres
Publié: (2024)

Superposition as Lossy Compression: Measure with Sparse Autoencoders and Connect to Adversarial Vulnerability
par: Bereska, Leonard, et autres
Publié: (2025)

Transferability Ranking of Adversarial Examples
par: Levy, Mosh, et autres
Publié: (2022)

Adversarial Attacks Leverage Interference Between Features in Superposition
par: Stevinson, Edward, et autres
Publié: (2025)

Laundering AI Authority with Adversarial Examples
par: Zhang, Jie, et autres
Publié: (2026)

MemLoss: Enhancing Adversarial Training with Recycling Adversarial Examples
par: Mahdi, Soroush, et autres
Publié: (2025)

Towards Interpretable Adversarial Examples via Sparse Adversarial Attack
par: Lin, Fudong, et autres
Publié: (2025)

Adversarial Examples Are Not Real Features
par: Li, Ang, et autres
Publié: (2023)

A New Type of Adversarial Examples
par: Nie, Xingyang, et autres
Publié: (2025)

Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial Robustness
par: Pal, Ambar, et autres
Publié: (2023)

Out-of-Distribution Data: An Acquaintance of Adversarial Examples -- A Survey
par: Karunanayake, Naveen, et autres
Publié: (2024)

Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization
par: Lin, Runqi, et autres
Publié: (2024)

Generating Less Certain Adversarial Examples Improves Robust Generalization
par: Zhang, Minxing, et autres
Publié: (2023)

Position: Towards Resilience Against Adversarial Examples
par: Dai, Sihui, et autres
Publié: (2024)

SoK: Analyzing Adversarial Examples: A Framework to Study Adversary Knowledge
par: Fenaux, Lucas, et autres
Publié: (2024)

Persistent Classification: A New Approach to Stability of Data and Adversarial Examples
par: Bell, Brian, et autres
Publié: (2024)

Geometric Kolmogorov-Arnold Superposition Theorem
par: Alesiani, Francesco, et autres
Publié: (2025)

Analyzing the Impact of Adversarial Examples on Explainable Machine Learning
par: Devabhakthini, Prathyusha, et autres
Publié: (2023)

Rectifying Adversarial Examples Using Their Vulnerabilities
par: Morimoto, Fumiya, et autres
Publié: (2026)

Attacking All Tasks at Once Using Adversarial Examples in Multi-Task Learning
par: Zhang, Lijun, et autres
Publié: (2023)

Adversarial Examples Detection with Bayesian Neural Network
par: Li, Yao, et autres
Publié: (2021)

Do Counterfactual Examples Complicate Adversarial Training?
par: Yeats, Eric, et autres
Publié: (2024)

Superposition in Graph Neural Networks
par: Pertl, Lukas, et autres
Publié: (2025)

Sparsity and Superposition in Mixture of Experts
par: Chaudhari, Marmik, et autres
Publié: (2025)

Mathematical Models of Computation in Superposition
par: Hänni, Kaarel, et autres
Publié: (2024)

Towards a Novel Perspective on Adversarial Examples Driven by Frequency
par: Zhang, Zhun, et autres
Publié: (2024)

Improved Generation of Adversarial Examples Against Safety-aligned LLMs
par: Li, Qizhang, et autres
Publié: (2024)

Constructing Semantics-Aware Adversarial Examples with a Probabilistic Perspective
par: Zhang, Andi, et autres
Publié: (2023)

Evaluating Text Classification Robustness to Part-of-Speech Adversarial Examples
par: Samadi, Anahita, et autres
Publié: (2024)

When and How to Fool Explainable Models (and Humans) with Adversarial Examples
par: Vadillo, Jon, et autres
Publié: (2021)

BLAZE: Cross-Language and Cross-Project Bug Localization via Dynamic Chunking and Hard Example Learning
par: Chakraborty, Partha, et autres
Publié: (2024)

Transferable Adversarial Examples with Bayes Approach
par: Fan, Mingyuan, et autres
Publié: (2022)

Where and How to Attack? A Causality-Inspired Recipe for Generating Counterfactual Adversarial Examples
par: Cai, Ruichu, et autres
Publié: (2023)

Learning Environment for the Air Domain (LEAD)
par: Strand, Andreas, et autres
Publié: (2023)

Challenging Bug Prediction and Repair Models with Synthetic Bugs
par: Ibrahimzada, Ali Reza, et autres
Publié: (2023)

Superposition disentanglement of neural representations reveals hidden alignment
par: Longon, André, et autres
Publié: (2025)