Information-Geometric Inverse Distillation for Enhancing Adversarial Transferability
cs.LG, cs.AI, cs.CV
Submitted: 2025-02-24
Updated: 2026-09-17
Comments: 13 pages, 4 figures
Code: https://github.com/ImmortalTing/IKD
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Explaining and Harnessing Adversarial Examples
- Distilling the Knowledge in a Neural Network
- Torchattacks: A PyTorch Repository for Adversarial Attacks
- Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks
- Towards Deep Learning Models Resistant to Adversarial Attacks
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Intriguing properties of neural networks
- Ensemble Adversarial Training: Attacks and Defenses
- Boosting Adversarial Transferability through Enhanced Momentum
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