Squeeze Training for Adversarial Robustness
The vulnerability of deep neural networks (DNNs) to adversarial examples has attracted great attention in the machine learning community. The problem is related to non-flatness and non-smoothness of normally obtained loss landscapes. Training augmented with adversarial examples (a.k.a., adversarial training) is considered as an effective remedy. In this paper, we highlight that some collaborative examples, nearly perceptually indistinguishable from both adversarial and benign examples yet show extremely lower prediction loss, can be utilized to enhance adversarial training. A novel method is therefore proposed to achieve new state-of-the-arts in adversarial robustness. Code: https://github.com/qizhangli/ST-AT.
Code (1)
Tasks
Adversarial RobustnessSimilar Papers 제목 키워드 기반
Towards Robust Training of Neural Networks by Regularizing Adversarial Gradients
In recent years, neural networks have demonstrated outstanding effectiveness in a large amount of applications.However, recent works have shown that neural networks are susceptible to adversarial examples, indicating pos…
Robust Principles: Architectural Design Principles for Adversarially Robust CNNs
Our research aims to unify existing works' diverging opinions on how architectural components affect the adversarial robustness of CNNs. To accomplish our goal, we synthesize a suite of three generalizable robust archite…
Adversarial RobustnessCurls & Whey: Boosting Black-Box Adversarial Attacks
Image classifiers based on deep neural networks suffer from harassment caused by adversarial examples. Two defects exist in black-box iterative attacks that generate adversarial examples by incrementally adjusting the no…
Adversarial AttackDiversityDefending Spiking Neural Networks against Adversarial Attacks through Image Purification
Spiking Neural Networks (SNNs) aim to bridge the gap between neuroscience and machine learning by emulating the structure of the human nervous system. However, like convolutional neural networks, SNNs are vulnerable to a…
DenoisingReward Under Attack: Analyzing the Robustness and Hackability of Process Reward Models
Process Reward Models (PRMs) are rapidly becoming the backbone of LLM reasoning pipelines, yet we demonstrate that state-of-the-art PRMs are systematically exploitable under adversarial optimization pressure. To address …