paper-with-me

홈 › Papers

Get Fooled for the Right Reason: Improving Adversarial Robustness through a Teacher-guided Curriculum Learning Approach

2021-10-30 · Anindya Sarkar, Anirban Sarkar, Sowrya Gali, Vineeth N Balasubramanian

Current SOTA adversarially robust models are mostly based on adversarial training (AT) and differ only by some regularizers either at inner maximization or outer minimization steps. Being repetitive in nature during the inner maximization step, they take a huge time to train. We propose a non-iterative method that enforces the following ideas during training. Attribution maps are more aligned to the actual object in the image for adversarially robust models compared to naturally trained models. Also, the allowed set of pixels to perturb an image (that changes model decision) should be restricted to the object pixels only, which reduces the attack strength by limiting the attack space. Our method achieves significant performance gains with a little extra effort (10-20%) over existing AT models and outperforms all other methods in terms of adversarial as well as natural accuracy. We have performed extensive experimentation with CIFAR-10, CIFAR-100, and TinyImageNet datasets and reported results against many popular strong adversarial attacks to prove the effectiveness of our method.

📄 PDF Abstract BibTeX arXiv:2111.00295

Code (1)

sowgali/get-fooled-for-the-right-reason 공식 구현 tf

Tasks

Adversarial Robustness

Similar Papers 제목 키워드 기반

Fooling Adversarial Training with Inducing Noise

2021-11-19 · Zhirui Wang, Yifei Wang, Yisen Wang

Adversarial training is widely believed to be a reliable approach to improve model robustness against adversarial attack. However, in this paper, we show that when trained on one type of poisoned data, adversarial traini…

Adversarial Attack

Fooling Adversarial Training with Induction Noise

2021-09-29 · Zhirui Wang, Yifei Wang, Yisen Wang

Adversarial training is widely believed to be a reliable approach to improve model robustness against adversarial attack. However, in this paper, we show that when trained on one type of poisoned data, adversarial traini…

Adversarial Attack

R-SNN: An Analysis and Design Methodology for Robustifying Spiking Neural Networks against Adversarial Attacks through Noise Filters for Dynamic Vision Sensors

2021-09-01 · Alberto Marchisio, Giacomo Pira, Maurizio Martina, Guido Masera 외

Spiking Neural Networks (SNNs) aim at providing energy-efficient learning capabilities when implemented on neuromorphic chips with event-based Dynamic Vision Sensors (DVS). This paper studies the robustness of SNNs again…

Corrupting Data to Remove Deceptive Perturbation: Using Preprocessing Method to Improve System Robustness

2022-01-05 · Hieu Le, Hans Walker, Dung Tran, Peter Chin

Although deep neural networks have achieved great performance on classification tasks, recent studies showed that well trained networks can be fooled by adding subtle noises. This paper introduces a new approach to impro…

Denoising

Robust Ensemble Model Training via Random Layer Sampling Against Adversarial Attack

2020-05-21 · Hakmin Lee, Hong Joo Lee, Seong Tae Kim, Yong Man Ro

Deep neural networks have achieved substantial achievements in several computer vision areas, but have vulnerabilities that are often fooled by adversarial examples that are not recognized by humans. This is an important…

Adversarial AttackAdversarial Robustness