paper-with-me

Papers

Squeeze Training for Adversarial Robustness

2022-05-23 · Qizhang Li, Yiwen Guo, WangMeng Zuo, Hao Chen

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.

📄 PDF Abstract BibTeX arXiv:2205.11156

Code (1)

qizhangli/st-at 공식 구현 pytorch

Tasks

Adversarial Robustness

Similar Papers 제목 키워드 기반

Towards Robust Training of Neural Networks by Regularizing Adversarial Gradients

2018-05-23 · Fuxun Yu, Zirui Xu, Yanzhi Wang, ChenChen Liu 외

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

2023-08-30 · Shengyun Peng, Weilin Xu, Cory Cornelius, Matthew Hull 외

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 Robustness

Curls & Whey: Boosting Black-Box Adversarial Attacks

2019-04-02 · CVPR 2019 6 · Yucheng Shi, Siyu Wang, Yahong Han

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 AttackDiversity

Defending Spiking Neural Networks against Adversarial Attacks through Image Purification

2024-04-26 · Weiran Chen, Qi Sun, Qi Xu

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…

Denoising

Reward Under Attack: Analyzing the Robustness and Hackability of Process Reward Models

2026-02-20 · Rishabh Tiwari, Aditya Tomar, Udbhav Bamba, Monishwaran Maheswaran 외 arxiv

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 …