Adaptive Adversarial Logits Pairing

2020-05-25 · Shangxi Wu, Jitao Sang, Kaiyuan Xu, Guanhua Zheng, Changsheng Xu

Adversarial examples provide an opportunity as well as impose a challenge for understanding image classification systems. Based on the analysis of the adversarial training solution Adversarial Logits Pairing (ALP), we observed in this work that: (1) The inference of adversarially robust model tends to rely on fewer high-contribution features compared with vulnerable ones. (2) The training target of ALP doesn't fit well to a noticeable part of samples, where the logits pairing loss is overemphasized and obstructs minimizing the classification loss. Motivated by these observations, we design an Adaptive Adversarial Logits Pairing (AALP) solution by modifying the training process and training target of ALP. Specifically, AALP consists of an adaptive feature optimization module with Guided Dropout to systematically pursue fewer high-contribution features, and an adaptive sample weighting module by setting sample-specific training weights to balance between logits pairing loss and classification loss. The proposed AALP solution demonstrates superior defense performance on multiple datasets with extensive experiments.

📄 PDF Abstract BibTeX arXiv:2005.11904

Code (0)

등록된 구현이 없습니다.

Tasks

Classification General Classification image-classification Image Classification

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Adversarial Logit Pairing

2018-03-16 · NeurIPS 2018 · Harini Kannan, Alexey Kurakin, Ian Goodfellow

In this paper, we develop improved techniques for defending against adversarial examples at scale. First, we implement the state of the art version of adversarial training at unprecedented scale on ImageNet and investiga…

Are Odds Really Odd? Bypassing Statistical Detection of Adversarial Examples

2019-07-28 · Hossein Hosseini, Sreeram Kannan, Radha Poovendran

Deep learning classifiers are known to be vulnerable to adversarial examples. A recent paper presented at ICML 2019 proposed a statistical test detection method based on the observation that logits of noisy adversarial e…

Random Logit Scaling: Defending Deep Neural Networks Against Black-Box Score-Based Adversarial Example Attacks

2026-07-16 · Hamid Dashtbani, Mehdi Dousti Gandomani, AmirMahdi Sadeghzadeh arxiv

Machine learning models are increasingly adapted in various domains. However, adversarial examples pose a significant threat to the reliable deployment of these models. In recent years, some powerful adversarial example …

CodeFort: Robust Training for Code Generation Models

2024-04-11 · Yuhao Zhang, Shiqi Wang, Haifeng Qian, Zijian Wang 외

Code generation models are not robust to small perturbations, which often lead to incorrect generations and significantly degrade the performance of these models. Although improving the robustness of code generation mode…

Code Generation Contrastive Learning Data Augmentation

Evaluating and Understanding the Robustness of Adversarial Logit Pairing

2018-07-26 · Logan Engstrom, Andrew Ilyas, Anish Athalye

We evaluate the robustness of Adversarial Logit Pairing, a recently proposed defense against adversarial examples. We find that a network trained with Adversarial Logit Pairing achieves 0.6% accuracy in the threat model …

Adversarial Attack