paper-with-me

Papers

Analyzing Accuracy Loss in Randomized Smoothing Defenses

2020-03-03 · Yue Gao, Harrison Rosenberg, Kassem Fawaz, Somesh Jha, Justin Hsu

Recent advances in machine learning (ML) algorithms, especially deep neural networks (DNNs), have demonstrated remarkable success (sometimes exceeding human-level performance) on several tasks, including face and speech recognition. However, ML algorithms are vulnerable to \emph{adversarial attacks}, such test-time, training-time, and backdoor attacks. In test-time attacks an adversary crafts adversarial examples, which are specially crafted perturbations imperceptible to humans which, when added to an input example, force a machine learning model to misclassify the given input example. Adversarial examples are a concern when deploying ML algorithms in critical contexts, such as information security and autonomous driving. Researchers have responded with a plethora of defenses. One promising defense is \emph{randomized smoothing} in which a classifier's prediction is smoothed by adding random noise to the input example we wish to classify. In this paper, we theoretically and empirically explore randomized smoothing. We investigate the effect of randomized smoothing on the feasible hypotheses space, and show that for some noise levels the set of hypotheses which are feasible shrinks due to smoothing, giving one reason why the natural accuracy drops after smoothing. To perform our analysis, we introduce a model for randomized smoothing which abstracts away specifics, such as the exact distribution of the noise. We complement our theoretical results with extensive experiments.

📄 PDF Abstract BibTeX arXiv:2003.01595

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingBIG-bench Machine Learningspeech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

Randomized Smoothing 설명 없음

Similar Papers 제목 키워드 기반

On Certifying Robustness against Backdoor Attacks via Randomized Smoothing

2020-02-26 · Binghui Wang, Xiaoyu Cao, Jinyuan Jia, Neil Zhenqiang Gong

Backdoor attack is a severe security threat to deep neural networks (DNNs). We envision that, like adversarial examples, there will be a cat-and-mouse game for backdoor attacks, i.e., new empirical defenses are developed…

Backdoor Attack

Rethinking Randomized Smoothing from the Perspective of Scalability

2023-12-19 · Anupriya Kumari, Devansh Bhardwaj, Sukrit Jindal

Machine learning models have demonstrated remarkable success across diverse domains but remain vulnerable to adversarial attacks. Empirical defense mechanisms often fail, as new attacks constantly emerge, rendering exist…

Survey

A Unified framework for randomized smoothing based certified defenses

2019-09-25 · Tianhang Zheng, Di Wang, Baochun Li, Jinhui Xu

Randomized smoothing, which was recently proved to be a certified defensive technique, has received considerable attention due to its scalability to large datasets and neural networks. However, several important question…

Randomized Smoothing of All Shapes and Sizes

2020-02-19 · ICML 2020 1 · Greg Yang, Tony Duan, J. Edward Hu, Hadi Salman 외

Randomized smoothing is the current state-of-the-art defense with provable robustness against $\ell_2$ adversarial attacks. Many works have devised new randomized smoothing schemes for other metrics, such as $\ell_1$ or …

All

Certified Adversarial Robustness of Machine Learning-based Malware Detectors via (De)Randomized Smoothing

2024-05-01 · Daniel Gibert, Luca Demetrio, Giulio Zizzo, Quan Le 외

Deep learning-based malware detection systems are vulnerable to adversarial EXEmples - carefully-crafted malicious programs that evade detection with minimal perturbation. As such, the community is dedicating effort to d…

Adversarial RobustnessMalware Detection