paper-with-me

홈 › Papers

Recent Advances in Understanding Adversarial Robustness of Deep Neural Networks

2020-11-03 · Tao Bai, Jinqi Luo, Jun Zhao

Adversarial examples are inevitable on the road of pervasive applications of deep neural networks (DNN). Imperceptible perturbations applied on natural samples can lead DNN-based classifiers to output wrong prediction with fair confidence score. It is increasingly important to obtain models with high robustness that are resistant to adversarial examples. In this paper, we survey recent advances in how to understand such intriguing property, i.e. adversarial robustness, from different perspectives. We give preliminary definitions on what adversarial attacks and robustness are. After that, we study frequently-used benchmarks and mention theoretically-proved bounds for adversarial robustness. We then provide an overview on analyzing correlations among adversarial robustness and other critical indicators of DNN models. Lastly, we introduce recent arguments on potential costs of adversarial training which have attracted wide attention from the research community.

📄 PDF Abstract BibTeX arXiv:2011.01539

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Robustness

Similar Papers 제목 키워드 기반

Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial Robustness

2020-10-19 · Guillermo Ortiz-Jimenez, Apostolos Modas, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard

Driven by massive amounts of data and important advances in computational resources, new deep learning systems have achieved outstanding results in a large spectrum of applications. Nevertheless, our current theoretical …

Adversarial RobustnessDeep Learning

A Frequency Perspective of Adversarial Robustness

2021-10-26 · Shishira R Maiya, Max Ehrlich, Vatsal Agarwal, Ser-Nam Lim 외

Adversarial examples pose a unique challenge for deep learning systems. Despite recent advances in both attacks and defenses, there is still a lack of clarity and consensus in the community about the true nature and unde…

Adversarial Robustness

Adversarial Reasoning at Jailbreaking Time

2025-02-03 · Mahdi Sabbaghi, Paul Kassianik, George Pappas, Yaron Singer 외

As large language models (LLMs) are becoming more capable and widespread, the study of their failure cases is becoming increasingly important. Recent advances in standardizing, measuring, and scaling test-time compute su…

Adversarial Robustness

Robust Natural Language Processing: Recent Advances, Challenges, and Future Directions

2022-01-03 · marwan omar, Soohyeon Choi, DaeHun Nyang, David Mohaisen

Recent natural language processing (NLP) techniques have accomplished high performance on benchmark datasets, primarily due to the significant improvement in the performance of deep learning. The advances in the research…

Sentiment Analysisspeech-recognitionSpeech Recognition

Recent Advances in Adversarial Training for Adversarial Robustness

2021-02-02 · Tao Bai, Jinqi Luo, Jun Zhao, Bihan Wen 외

Adversarial training is one of the most effective approaches defending against adversarial examples for deep learning models. Unlike other defense strategies, adversarial training aims to promote the robustness of models…

Adversarial Robustness