paper-with-me

Papers

Provably Safeguarding a Classifier from OOD and Adversarial Samples: an Extreme Value Theory Approach

2025-01-17 · Nicolas Atienza, Christophe Labreuche, Johanne Cohen, Michele Sebag

This paper introduces a novel method, Sample-efficient Probabilistic Detection using Extreme Value Theory (SPADE), which transforms a classifier into an abstaining classifier, offering provable protection against out-of-distribution and adversarial samples. The approach is based on a Generalized Extreme Value (GEV) model of the training distribution in the classifier's latent space, enabling the formal characterization of OOD samples. Interestingly, under mild assumptions, the GEV model also allows for formally characterizing adversarial samples. The abstaining classifier, which rejects samples based on their assessment by the GEV model, provably avoids OOD and adversarial samples. The empirical validation of the approach, conducted on various neural architectures (ResNet, VGG, and Vision Transformer) and medium and large-sized datasets (CIFAR-10, CIFAR-100, and ImageNet), demonstrates its frugality, stability, and efficiency compared to the state of the art.

📄 PDF Abstract BibTeX arXiv:2501.10202

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Adversarial Text Purification: A Large Language Model Approach for Defense

2024-02-05 · Raha Moraffah, Shubh Khandelwal, Amrita Bhattacharjee, Huan Liu

Adversarial purification is a defense mechanism for safeguarding classifiers against adversarial attacks without knowing the type of attacks or training of the classifier. These techniques characterize and eliminate adve…

Adversarial PurificationAdversarial TextLanguage ModelingLanguage Modelling+2

Provably Robust Detection of Out-of-distribution Data (almost) for free

2021-06-08 · Alexander Meinke, Julian Bitterwolf, Matthias Hein

The application of machine learning in safety-critical systems requires a reliable assessment of uncertainty. However, deep neural networks are known to produce highly overconfident predictions on out-of-distribution (OO…

Out of Distribution (OOD) Detection

Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers

2019-06-09 · NeurIPS 2019 12 · Hadi Salman, Greg Yang, Jerry Li, Pengchuan Zhang 외

Recent works have shown the effectiveness of randomized smoothing as a scalable technique for building neural network-based classifiers that are provably robust to $\ell_2$-norm adversarial perturbations. In this paper, …

Adversarial AttackAdversarial DefenseDeep Learning

Confidence-aware Training of Smoothed Classifiers for Certified Robustness

2022-12-18 · Jongheon Jeong, Seojin Kim, Jinwoo Shin

Any classifier can be "smoothed out" under Gaussian noise to build a new classifier that is provably robust to $\ell_2$-adversarial perturbations, viz., by averaging its predictions over the noise via randomized smoothin…

Adversarial Robustness

PAC-Learning for Strategic Classification

2020-12-06 · Ravi Sundaram, Anil Vullikanti, Haifeng Xu, Fan Yao

The study of strategic or adversarial manipulation of testing data to fool a classifier has attracted much recent attention. Most previous works have focused on two extreme situations where any testing data point either …

ClassificationGeneral ClassificationPAC learning