Abstract
Deep neural networks are easily fooled high confidence predictions for adversarial samples
Generating Minimal Adversarial Perturbations with Integrated Adaptive Gradients
Related papers
Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).
- On Detecting Adversarial Perturbations (2017)70% match
- The Limitations of Deep Learning in Adversarial Settings (2015)69% match
- Detecting Adversarial Image Examples in Deep Networks with Adaptive Noise Reduction (2017)69% match
- Learning Universal Adversarial Perturbations with Generative Models (2017)68% match
- Adversarial Attacks on Deepfake Detectors: A GAN-Based Approach for Generating Imperceptible Perturbations (2026)68% match
- Adversarial Example Defense Via Perturbation Grading Strategy (2022)68% match
- Generating Adversarial Examples with Adversarial Networks (2018)67% match
- A Data Augmentation-based Defense Method Against Adversarial Attacks in Neural Networks (2020)67% match