English
Related papers

Related papers: Random Smoothing Might be Unable to Certify $\ell_…

200 papers

Deep-learning-based NLP models are found to be vulnerable to word substitution perturbations. Before they are widely adopted, the fundamental issues of robustness need to be addressed. Along this line, we propose a formal framework to…

Computation and Language · Computer Science 2022-01-12 Yuting Yang , Pei Huang , FeiFei Ma , Juan Cao , Meishan Zhang , Jian Zhang , Jintao Li

Neural networks have been shown to be vulnerable against minor adversarial perturbations of their inputs, especially for high dimensional data under $\ell_\infty$ attacks. To combat this problem, techniques like adversarial training have…

Machine Learning · Computer Science 2019-06-04 Emilio Rafael Balda , Arash Behboodi , Niklas Koep , Rudolf Mathar

Generative learning, recognized for its effective modeling of data distributions, offers inherent advantages in handling out-of-distribution instances, especially for enhancing robustness to adversarial attacks. Among these, diffusion…

Machine Learning · Computer Science 2025-02-25 Huanran Chen , Yinpeng Dong , Shitong Shao , Zhongkai Hao , Xiao Yang , Hang Su , Jun Zhu

Randomized smoothing is a recent technique that achieves state-of-art performance in training certifiably robust deep neural networks. While the smoothing family of distributions is often connected to the choice of the norm used for…

Machine Learning · Computer Science 2022-07-06 Motasem Alfarra , Adel Bibi , Philip H. S. Torr , Bernard Ghanem

In most practical problems of classifier learning, the training data suffers from the label noise. Hence, it is important to understand how robust is a learning algorithm to such label noise. This paper presents some theoretical analysis to…

Machine Learning · Computer Science 2016-08-29 Aritra Ghosh , Naresh Manwani , P. S. Sastry

Trustworthy machine learning necessitates meticulous regulation of model reliance on non-robust features. We propose a framework to delineate and regulate such features by attributing model predictions to the input. Within our approach,…

Machine Learning · Computer Science 2024-07-10 Peiyu Yang , Naveed Akhtar , Mubarak Shah , Ajmal Mian

We study the question of testing structured properties (classes) of discrete distributions. Specifically, given sample access to an arbitrary distribution $D$ over $[n]$ and a property $\mathcal{P}$, the goal is to distinguish between…

Data Structures and Algorithms · Computer Science 2016-01-22 Clément L. Canonne , Ilias Diakonikolas , Themis Gouleakis , Ronitt Rubinfeld

Along with recent diffusion models, randomized smoothing has become one of a few tangible approaches that offers adversarial robustness to models at scale, e.g., those of large pre-trained models. Specifically, one can perform randomized…

Machine Learning · Computer Science 2023-10-30 Jongheon Jeong , Jinwoo Shin

Adversarial perturbations dramatically decrease the accuracy of state-of-the-art image classifiers. In this paper, we propose and analyze a simple and computationally efficient defense strategy: inject random Gaussian noise, discretize each…

Machine Learning · Computer Science 2019-03-27 Yuchen Zhang , Percy Liang

Methods to certify the robustness of neural networks in the presence of input uncertainty are vital in safety-critical settings. Most certification methods in the literature are designed for adversarial input uncertainty, but researchers…

Machine Learning · Computer Science 2023-01-26 Brendon G. Anderson , Somayeh Sojoudi

Prior work has explored directly regularizing the output distributions of probabilistic models to alleviate peaky (i.e. over-confident) predictions, a common sign of overfitting. This class of techniques, of which label smoothing is one,…

Computation and Language · Computer Science 2020-05-13 Clara Meister , Elizabeth Salesky , Ryan Cotterell

Labelling of data for supervised learning can be costly and time-consuming and the risk of incorporating label noise in large data sets is imminent. When training a flexible discriminative model using a strictly proper loss, such noise will…

Machine Learning · Statistics 2022-05-13 Amanda Olmin , Fredrik Lindsten

We propose Adaptive Diffusion Denoised Smoothing, a method for certifying the predictions of a vision model against adversarial examples, while adapting to the input. Our key insight is to reinterpret a guided denoising diffusion model as a…

Computer Vision and Pattern Recognition · Computer Science 2025-07-14 Frederick Shpilevskiy , Saiyue Lyu , Krishnamurthy Dj Dvijotham , Mathias Lécuyer , Pierre-André Noël

Several existing works study either adversarial or natural distributional robustness of deep neural networks separately. In practice, however, models need to enjoy both types of robustness to ensure reliability. In this work, we bridge this…

Machine Learning · Computer Science 2022-09-19 Mazda Moayeri , Kiarash Banihashem , Soheil Feizi

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 to defend against…

Cryptography and Security · Computer Science 2020-07-21 Binghui Wang , Xiaoyu Cao , Jinyuan jia , Neil Zhenqiang Gong

This paper tackles the problem of defending a neural network against adversarial attacks crafted with different norms (in particular $\ell_\infty$ and $\ell_2$ bounded adversarial examples). It has been observed that defense mechanisms…

Machine Learning · Computer Science 2020-02-14 Alexandre Araujo , Laurent Meunier , Rafael Pinot , Benjamin Negrevergne

The problem of adversarial examples has shown that modern Neural Network (NN) models could be rather fragile. Among the more established techniques to solve the problem, one is to require the model to be {\it $\epsilon$-adversarially…

Machine Learning · Computer Science 2020-11-17 Yuxin Wen , Shuai Li , Kui Jia

Recent work have demonstrated that robustness (to "corruption") can be at odds with generalization. Adversarial training, for instance, aims to reduce the problematic susceptibility of modern neural networks to small data perturbations.…

Machine Learning · Statistics 2023-05-19 Amine Bennouna , Ryan Lucas , Bart Van Parys

Random subspaces $X$ of $\mathbb{R}^n$ of dimension proportional to $n$ are, with high probability, well-spread with respect to the $\ell_2$-norm. Namely, every nonzero $x \in X$ is "robustly non-sparse" in the following sense: $x$ is…

Computational Complexity · Computer Science 2024-07-11 Venkatesan Guruswami , Peter Manohar , Jonathan Mosheiff

A fundamental problem in adversarial machine learning is to quantify how much training data is needed in the presence of evasion attacks. In this paper we address this issue within the framework of PAC learning, focusing on the class of…

Machine Learning · Computer Science 2022-05-13 Pascale Gourdeau , Varun Kanade , Marta Kwiatkowska , James Worrell