Cover Image

A Vulnerability of Attribution Methods Using Pre-Softmax Scores

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lerma, Miguel, Lucas, Mirtha
Format:	Preprint
Published:	2023
Subjects:	Machine Learning Artificial Intelligence 68T07 I.2.m
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Bridging Traffic State and Trajectory for Dynamic Road Network and Trajectory Representation Learning
by: Han, Chengkai, et al.
Published: (2025)

L3AC: Towards a Lightweight and Lossless Audio Codec
by: Zhai, Linwei, et al.
Published: (2025)

From Features to Graphs: Exploring Graph Structures and Pairwise Interactions via GNNs
by: Yamchote, Phaphontee, et al.
Published: (2025)

TaylorShift: Shifting the Complexity of Self-Attention from Squared to Linear (and Back) using Taylor-Softmax
by: Nauen, Tobias Christian, et al.
Published: (2024)

CRUPL: A Semi-Supervised Cyber Attack Detection with Consistency Regularization and Uncertainty-aware Pseudo-Labeling in Smart Grid
by: Dash, Smruti P., et al.
Published: (2025)

A Machine Learning Framework for Turbofan Health Estimation via Inverse Problem Formulation
by: Leyli-Abadi, Milad, et al.
Published: (2026)

Power-Efficient Image Storage: Leveraging Super Resolution Generative Adversarial Network for Sustainable Compression and Reduced Carbon Footprint
by: Mondal, Ashok, et al.
Published: (2024)

GRALIS: A Unified Canonical Framework for Linear Attribution Methods via Riesz Representation
by: Fanale, Raimondo
Published: (2026)

Concept Prerequisite Relation Prediction by Using Permutation-Equivariant Directed Graph Neural Networks
by: Qu, Xiran, et al.
Published: (2023)

Alternative positional encoding functions for neural transformers
by: Lopez-Rubio, Ezequiel, et al.
Published: (2025)

CVCM Track Circuits Pre-emptive Failure Diagnostics for Predictive Maintenance Using Deep Neural Networks
by: Mukherjee, Debdeep, et al.
Published: (2025)

Communications to Circulations: Real-Time 3D Wind Field Prediction Using 5G GNSS Signals and Deep Learning
by: Ye, Yuchen, et al.
Published: (2025)

ProactBench: Beyond What The User Asked For
by: Harfi, Sepehr, et al.
Published: (2026)

Lost or Hidden? A Concept-Level Forgetting in Supervised Continual Learning
by: Filus, Katarzyna, et al.
Published: (2026)

Queue up for takeoff: a transferable deep learning framework for flight delay prediction
by: Aghanya, Nnamdi Daniel, et al.
Published: (2025)

Deceptive Diffusion: Generating Synthetic Adversarial Examples
by: Beerens, Lucas, et al.
Published: (2024)

A Practical Guide to Streaming Continual Learning
by: Cossu, Andrea, et al.
Published: (2026)

HGTUL: A Hypergraph-based Model For Trajectory User Linking
by: Chang, Fengjie, et al.
Published: (2025)

Energy-Efficient Deep Learning Without Backpropagation: A Rigorous Evaluation of Forward-Only Algorithms
by: Spyra, Przemysław, et al.
Published: (2025)

How Pruning Reshapes Features: Sparse Autoencoder Analysis of Weight-Pruned Language Models
by: Borobia, Hector, et al.
Published: (2026)

The Concept Allocation Zone: Tracking How Concepts Form Across Transformer Depth
by: Henry, James
Published: (2026)

On Privacy Leakage in Tabular Diffusion Models: Influential Factors, Attacker Knowledge, and Metrics
by: Shafieinejad, Masoumeh, et al.
Published: (2026)

Don't Look Back in Anger: MAGIC Net for Streaming Continual Learning with Temporal Dependence
by: Giannini, Federico, et al.
Published: (2026)

cPNN: Continuous Progressive Neural Networks for Evolving Streaming Time Series
by: Giannini, Federico, et al.
Published: (2026)

Faked Speech Detection with Zero Prior Knowledge
by: Ajmi, Sahar Al, et al.
Published: (2022)

DNNShifter: An Efficient DNN Pruning System for Edge Computing
by: Eccles, Bailey J., et al.
Published: (2023)

HyperMask: Adaptive Hypernetwork-based Masks for Continual Learning
by: Książek, Kamil, et al.
Published: (2023)

Conditional Temporal Neural Processes with Covariance Loss
by: Yoo, Boseon, et al.
Published: (2025)

Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection
by: Wu, Chengcan, et al.
Published: (2025)

Tazza: Shuffling Neural Network Parameters for Secure and Private Federated Learning
by: Lee, Kichang, et al.
Published: (2024)

Is ReLU Adversarially Robust?
by: Sooksatra, Korn, et al.
Published: (2024)

Interpretability Can Be Actionable
by: Orgad, Hadas, et al.
Published: (2026)

Upside Down Reinforcement Learning with Policy Generators
by: Di Ventura, Jacopo, et al.
Published: (2025)

Multi-Level Fusion Graph Neural Network for Molecule Property Prediction
by: Liu, XiaYu, et al.
Published: (2025)

Probing for Representation Manifolds in Superposition
by: Modell, Alexander
Published: (2026)

CGLearn: Consistent Gradient-Based Learning for Out-of-Distribution Generalization
by: Chowdhury, Jawad, et al.
Published: (2024)

The Origins of Representation Manifolds in Large Language Models
by: Modell, Alexander, et al.
Published: (2025)

Improving Time Series Classification with Representation Soft Label Smoothing
by: Ma, Hengyi, et al.
Published: (2024)

Simple Network Graph Comparative Learning
by: Yu, Qiang, et al.
Published: (2026)

Mapping representations in Reinforcement Learning via Semantic Alignment for Zero-Shot Stitching
by: Ricciardi, Antonio Pio, et al.
Published: (2025)