paper-with-me

Papers

Beyond Perturbations: Learning Guarantees with Arbitrary Adversarial Test Examples

2020-07-10 · NeurIPS 2020 12 · Shafi Goldwasser, Adam Tauman Kalai, Yael Tauman Kalai, Omar Montasser

We present a transductive learning algorithm that takes as input training examples from a distribution $P$ and arbitrary (unlabeled) test examples, possibly chosen by an adversary. This is unlike prior work that assumes that test examples are small perturbations of $P$. Our algorithm outputs a selective classifier, which abstains from predicting on some examples. By considering selective transductive learning, we give the first nontrivial guarantees for learning classes of bounded VC dimension with arbitrary train and test distributions---no prior guarantees were known even for simple classes of functions such as intervals on the line. In particular, for any function in a class $C$ of bounded VC dimension, we guarantee a low test error rate and a low rejection rate with respect to $P$. Our algorithm is efficient given an Empirical Risk Minimizer (ERM) for $C$. Our guarantees hold even for test examples chosen by an unbounded white-box adversary. We also give guarantees for generalization, agnostic, and unsupervised settings.

📄 PDF Abstract BibTeX arXiv:2007.05145

Code (0)

등록된 구현이 없습니다.

Tasks

Transductive Learning

Similar Papers 제목 키워드 기반

Verifiably Robust Conformal Prediction

2024-05-29 · Linus Jeary, Tom Kuipers, Mehran Hosseini, Nicola Paoletti

Conformal Prediction (CP) is a popular uncertainty quantification method that provides distribution-free, statistically valid prediction sets, assuming that training and test data are exchangeable. In such a case, CP's p…

Conformal PredictionDeep Reinforcement Learningimage-classificationImage Classification+4

Adversarial Learning Guarantees for Linear Hypotheses and Neural Networks

2020-04-28 · ICML 2020 1 · Pranjal Awasthi, Natalie Frank, Mehryar Mohri

Adversarial or test time robustness measures the susceptibility of a classifier to perturbations to the test input. While there has been a flurry of recent work on designing defenses against such perturbations, the theor…

Adversarial Robustness

Fair Classification with Adversarial Perturbations

2021-06-10 · NeurIPS 2021 12 · L. Elisa Celis, Anay Mehrotra, Nisheeth K. Vishnoi

We study fair classification in the presence of an omniscient adversary that, given an $\eta$, is allowed to choose an arbitrary $\eta$-fraction of the training samples and arbitrarily perturb their protected attributes.…

ClassificationFairnessImputation

DDDM: a Brain-Inspired Framework for Robust Classification

2022-05-01 · Xiyuan Chen, Xingyu Li, Yi Zhou, Tianming Yang

Despite their outstanding performance in a broad spectrum of real-world tasks, deep artificial neural networks are sensitive to input noises, particularly adversarial perturbations. On the contrary, human and animal brai…

ClassificationDecision MakingRobust classificationtext-classification+1

Deterministic Certification of Graph Neural Networks against Graph Poisoning Attacks with Arbitrary Perturbations

2025-03-24 · CVPR 2025 1 · Jiate Li, Meng Pang, Yun Dong, Binghui Wang

Graph neural networks (GNNs) are becoming the de facto method to learn on the graph data and have achieved the state-of-the-art on node and graph classification tasks. However, recent works show GNNs are vulnerable to tr…

Graph Classification