Open-set Adversarial Defense

2020-09-02 · ECCV 2020 8 · Rui Shao, Pramuditha Perera, Pong C. Yuen, Vishal M. Patel

Open-set recognition and adversarial defense study two key aspects of deep learning that are vital for real-world deployment. The objective of open-set recognition is to identify samples from open-set classes during testing, while adversarial defense aims to defend the network against images with imperceptible adversarial perturbations. In this paper, we show that open-set recognition systems are vulnerable to adversarial attacks. Furthermore, we show that adversarial defense mechanisms trained on known classes do not generalize well to open-set samples. Motivated by this observation, we emphasize the need of an Open-Set Adversarial Defense (OSAD) mechanism. This paper proposes an Open-Set Defense Network (OSDN) as a solution to the OSAD problem. The proposed network uses an encoder with feature-denoising layers coupled with a classifier to learn a noise-free latent feature representation. Two techniques are employed to obtain an informative latent feature space with the objective of improving open-set performance. First, a decoder is used to ensure that clean images can be reconstructed from the obtained latent features. Then, self-supervision is used to ensure that the latent features are informative enough to carry out an auxiliary task. We introduce a testing protocol to evaluate OSAD performance and show the effectiveness of the proposed method in multiple object classification datasets. The implementation code of the proposed method is available at: https://github.com/rshaojimmy/ECCV2020-OSAD.

📄 PDF Abstract BibTeX arXiv:2009.00814

Code (1)

rshaojimmy/ECCV2020-OSAD 공식 구현 pytorch

Tasks

Adversarial Defense Decoder DenoisingOpen Set Learning

Open-set Adversarial Defense with Clean-Adversarial Mutual Learning

2022-02-12 · Rui Shao, Pramuditha Perera, Pong C. Yuen, Vishal M. Patel

Adversarial Defense Denoising image-classification Image Classification+1

Advocating for Multiple Defense Strategies against Adversarial Examples

2020-12-04 · Alexandre Araujo, Laurent Meunier, Rafael Pinot, Benjamin Negrevergne

It has been empirically observed that defense mechanisms designed to protect neural networks against $\ell_\infty$ adversarial examples offer poor performance against $\ell_2$ adversarial examples and vice versa. In this…

Large Language Model Sentinel: LLM Agent for Adversarial Purification

2024-05-24 · Guang Lin, Toshihisa Tanaka, Qibin Zhao

Over the past two years, the use of large language models (LLMs) has advanced rapidly. While these LLMs offer considerable convenience, they also raise security concerns, as LLMs are vulnerable to adversarial attacks by …

Adversarial Defense Adversarial Purification Adversarial Robustness Language Modeling+3

Adversarial Machine Learning: Attacks, Defenses, and Open Challenges

2025-02-08 · Pranav K Jha

Adversarial Machine Learning (AML) addresses vulnerabilities in AI systems where adversaries manipulate inputs or training data to degrade performance. This article provides a comprehensive analysis of evasion and poison…

IDEA: Invariant Defense for Graph Adversarial Robustness

2023-05-25 · Shuchang Tao, Qi Cao, HuaWei Shen, Yunfan Wu 외

Despite the success of graph neural networks (GNNs), their vulnerability to adversarial attacks poses tremendous challenges for practical applications. Existing defense methods suffer from severe performance decline unde…

Adversarial Robustness