Don't Waste the Noise: Importance-Guided Perturbation Allocation under Joint Global and Local Constraints
cs.LG, cs.AI, cs.CV
Submitted: 2026-10-01
Updated: 2026-10-01
Terminology
Sources
- Towards Evaluating the Robustness of Neural Networks
- EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples
- RobustBench: a standardized adversarial robustness benchmark
- Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attacks
- Sparse and Imperceivable Adversarial Attacks
- Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks
- Mind the box: $l_1$-APGD for sparse adversarial attacks on image classifiers
- Decoupled Kullback-Leibler Divergence Loss
- Saliency Attack: Towards Imperceptible Black-box Adversarial Attack
- A Light Recipe to Train Robust Vision Transformers
- GreedyFool: Distortion-Aware Sparse Adversarial Attack
- A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking
- SGDR: Stochastic Gradient Descent with Warm Restarts
- Towards Deep Learning Models Resistant to Adversarial Attacks
- SparseFool: a few pixels make a big difference
- DeepFool: a simple and accurate method to fool deep neural networks
- The Limitations of Deep Learning in Adversarial Settings
- Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints
- Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
- Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks