Enhancing Adversarial Transferability via Information Bottleneck Constraints
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909219771383808 |
|---|---|
| author | Qi, Biqing Gao, Junqi Liu, Jianxing Wu, Ligang Zhou, Bowen |
| author_facet | Qi, Biqing Gao, Junqi Liu, Jianxing Wu, Ligang Zhou, Bowen |
| contents | From the perspective of information bottleneck (IB) theory, we propose a novel framework for performing black-box transferable adversarial attacks named IBTA, which leverages advancements in invariant features. Intuitively, diminishing the reliance of adversarial perturbations on the original data, under equivalent attack performance constraints, encourages a greater reliance on invariant features that contributes most to classification, thereby enhancing the transferability of adversarial attacks. Building on this motivation, we redefine the optimization of transferable attacks using a novel theoretical framework that centers around IB. Specifically, to overcome the challenge of unoptimizable mutual information, we propose a simple and efficient mutual information lower bound (MILB) for approximating computation. Moreover, to quantitatively evaluate mutual information, we utilize the Mutual Information Neural Estimator (MINE) to perform a thorough analysis. Our experiments on the ImageNet dataset well demonstrate the efficiency and scalability of IBTA and derived MILB. Our code is available at https://github.com/Biqing-Qi/Enhancing-Adversarial-Transferability-via-Information-Bottleneck-Constraints. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_05531 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing Adversarial Transferability via Information Bottleneck Constraints Qi, Biqing Gao, Junqi Liu, Jianxing Wu, Ligang Zhou, Bowen Machine Learning Artificial Intelligence From the perspective of information bottleneck (IB) theory, we propose a novel framework for performing black-box transferable adversarial attacks named IBTA, which leverages advancements in invariant features. Intuitively, diminishing the reliance of adversarial perturbations on the original data, under equivalent attack performance constraints, encourages a greater reliance on invariant features that contributes most to classification, thereby enhancing the transferability of adversarial attacks. Building on this motivation, we redefine the optimization of transferable attacks using a novel theoretical framework that centers around IB. Specifically, to overcome the challenge of unoptimizable mutual information, we propose a simple and efficient mutual information lower bound (MILB) for approximating computation. Moreover, to quantitatively evaluate mutual information, we utilize the Mutual Information Neural Estimator (MINE) to perform a thorough analysis. Our experiments on the ImageNet dataset well demonstrate the efficiency and scalability of IBTA and derived MILB. Our code is available at https://github.com/Biqing-Qi/Enhancing-Adversarial-Transferability-via-Information-Bottleneck-Constraints. |
| title | Enhancing Adversarial Transferability via Information Bottleneck Constraints |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2406.05531 |