paper-with-me

Papers

Improving Adversarial Robustness via Information Bottleneck Distillation

2023-09-21 · NeurIPS 2023 11

Previous studies have shown that optimizing the information bottleneck can significantly improve the robustness of deep neural networks. Our study closely examines the information bottleneck principle and proposes an Information Bottleneck Distillation approach. This specially designed, robust distillation technique utilizes prior knowledge obtained from a robust pre-trained model to boost information bottlenecks. Specifically, we propose two distillation strategies that align with the two optimization processes of the information bottleneck. Firstly, we use a robust soft-label distillation method to increase the mutual information between latent features and output prediction. Secondly, we introduce an adaptive feature distillation method that automatically transfers relevant knowledge from the teacher model to the student model, thereby reducing the mutual information between the input and latent features. We conduct extensive experiments to evaluate our approach's robustness against state-of-the-art adversarial attackers such as PGD-attack and AutoAttack. Our experimental results demonstrate the effectiveness of our approach in significantly improving adversarial robustness. Our code is available at https://github.com/SkyKuang/IBD.Submission Number: 1797

📄 PDF Abstract BibTeX

Code (1)

skykuang/ibd 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Improving the Robustness/Accuracy Tradeoff Against Adversarial Attacks Using Information Bottleneck Distillation Through Dual Teachers

2026-07-30 · Vincent Ryusuke Takahashi, Yoshinari Takeishi, Jun'ichi Takeuchi, Kave Salamatian arxiv

Deep neural networks (DNNs) have achieved remarkable success in classical machine learning problems. However, they are known to be vulnerable to adversarial attacks. Countermeasures proposed in the literature, notably In…

A Closer Look at the Adversarial Robustness of Information Bottleneck Models

2021-07-12 · ICML Workshop AML 2021 7 · Iryna Korshunova, David Stutz, Alexander A. Alemi, Olivia Wiles 외

We study the adversarial robustness of information bottleneck models for classification. Previous works showed that the robustness of models trained with information bottlenecks can improve upon adversarial training. Our…

Adversarial Robustness

Pruning Adversarially Robust Neural Networks without Adversarial Examples

2022-10-09 · Tong Jian, Zifeng Wang, Yanzhi Wang, Jennifer Dy 외

Adversarial pruning compresses models while preserving robustness. Current methods require access to adversarial examples during pruning. This significantly hampers training efficiency. Moreover, as new adversarial attac…

Adversarial Robustness

Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustness

2021-06-04 · NeurIPS 2021 12 · Zifeng Wang, Tong Jian, Aria Masoomi, Stratis Ioannidis 외

We investigate the HSIC (Hilbert-Schmidt independence criterion) bottleneck as a regularizer for learning an adversarially robust deep neural network classifier. In addition to the usual cross-entropy loss, we add regula…

Adversarial Robustness

Adversarial Robustness of Bottleneck Injected Deep Neural Networks for Task-Oriented Communication

2024-12-13 · Alireza Furutanpey, Pantelis A. Frangoudis, Patrik Szabo, Schahram Dustdar

This paper investigates the adversarial robustness of Deep Neural Networks (DNNs) using Information Bottleneck (IB) objectives for task-oriented communication systems. We empirically demonstrate that while IB-based appro…

Adversarial Robustness