Adaptive Certified Training: Towards Better Accuracy-Robustness
Tradeoffs
- URL: http://arxiv.org/abs/2307.13078v1
- Date: Mon, 24 Jul 2023 18:59:46 GMT
- Title: Adaptive Certified Training: Towards Better Accuracy-Robustness
Tradeoffs
- Authors: Zhakshylyk Nurlanov, Frank R. Schmidt, Florian Bernard
- Abstract summary: We propose a novel certified training method based on a key insight that training with adaptive certified radii helps to improve the accuracy and robustness of the model.
We demonstrate the effectiveness of the proposed method on MNIST, CIFAR-10, and TinyImageNet datasets.
- Score: 17.46692880231195
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: As deep learning models continue to advance and are increasingly utilized in
real-world systems, the issue of robustness remains a major challenge. Existing
certified training methods produce models that achieve high provable robustness
guarantees at certain perturbation levels. However, the main problem of such
models is a dramatically low standard accuracy, i.e. accuracy on clean
unperturbed data, that makes them impractical. In this work, we consider a more
realistic perspective of maximizing the robustness of a model at certain levels
of (high) standard accuracy. To this end, we propose a novel certified training
method based on a key insight that training with adaptive certified radii helps
to improve both the accuracy and robustness of the model, advancing
state-of-the-art accuracy-robustness tradeoffs. We demonstrate the
effectiveness of the proposed method on MNIST, CIFAR-10, and TinyImageNet
datasets. Particularly, on CIFAR-10 and TinyImageNet, our method yields models
with up to two times higher robustness, measured as an average certified radius
of a test set, at the same levels of standard accuracy compared to baseline
approaches.
Related papers
- Weak Supervision Performance Evaluation via Partial Identification [46.73061437177238]
Programmatic Weak Supervision (PWS) enables supervised model training without direct access to ground truth labels.
We present a novel method to address this challenge by framing model evaluation as a partial identification problem.
Our approach derives reliable bounds on key metrics without requiring labeled data, overcoming core limitations in current weak supervision evaluation techniques.
arXiv Detail & Related papers (2023-12-07T07:15:11Z) - QualEval: Qualitative Evaluation for Model Improvement [82.73561470966658]
We propose QualEval, which augments quantitative scalar metrics with automated qualitative evaluation as a vehicle for model improvement.
QualEval uses a powerful LLM reasoner and our novel flexible linear programming solver to generate human-readable insights.
We demonstrate that leveraging its insights, for example, improves the absolute performance of the Llama 2 model by up to 15% points relative.
arXiv Detail & Related papers (2023-11-06T00:21:44Z) - Towards Calibrated Robust Fine-Tuning of Vision-Language Models [97.19901765814431]
This work proposes a robust fine-tuning method that improves both OOD accuracy and confidence calibration simultaneously in vision language models.
We show that both OOD classification and OOD calibration errors have a shared upper bound consisting of two terms of ID data.
Based on this insight, we design a novel framework that conducts fine-tuning with a constrained multimodal contrastive loss enforcing a larger smallest singular value.
arXiv Detail & Related papers (2023-11-03T05:41:25Z) - Towards Certified Probabilistic Robustness with High Accuracy [3.957941698534126]
Adrial examples pose a security threat to many critical systems built on neural networks.
How to build certifiably robust yet accurate neural network models remains an open problem.
We propose a novel approach that aims to achieve both high accuracy and certified probabilistic robustness.
arXiv Detail & Related papers (2023-09-02T09:39:47Z) - Post-hoc Uncertainty Learning using a Dirichlet Meta-Model [28.522673618527417]
We propose a novel Bayesian meta-model to augment pre-trained models with better uncertainty quantification abilities.
Our proposed method requires no additional training data and is flexible enough to quantify different uncertainties.
We demonstrate our proposed meta-model approach's flexibility and superior empirical performance on these applications.
arXiv Detail & Related papers (2022-12-14T17:34:11Z) - On the Importance of Calibration in Semi-supervised Learning [13.859032326378188]
State-of-the-art (SOTA) semi-supervised learning (SSL) methods have been highly successful in leveraging a mix of labeled and unlabeled data.
We introduce a family of new SSL models that optimize for calibration and demonstrate their effectiveness across standard vision benchmarks.
arXiv Detail & Related papers (2022-10-10T15:41:44Z) - (Certified!!) Adversarial Robustness for Free! [116.6052628829344]
We certify 71% accuracy on ImageNet under adversarial perturbations constrained to be within a 2-norm of 0.5.
We obtain these results using only pretrained diffusion models and image classifiers, without requiring any fine tuning or retraining of model parameters.
arXiv Detail & Related papers (2022-06-21T17:27:27Z) - Uncertainty-sensitive Activity Recognition: a Reliability Benchmark and
the CARING Models [37.60817779613977]
We present the first study of how welthe confidence values of modern action recognition architectures indeed reflect the probability of the correct outcome.
We introduce a new approach which learns to transform the model output into realistic confidence estimates through an additional calibration network.
arXiv Detail & Related papers (2021-01-02T15:41:21Z) - Learnable Boundary Guided Adversarial Training [66.57846365425598]
We use the model logits from one clean model to guide learning of another one robust model.
We achieve new state-of-the-art robustness on CIFAR-100 without additional real or synthetic data.
arXiv Detail & Related papers (2020-11-23T01:36:05Z) - Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness
and Accuracy for Free [115.81899803240758]
Adversarial training and its many variants substantially improve deep network robustness, yet at the cost of compromising standard accuracy.
This paper asks how to quickly calibrate a trained model in-situ, to examine the achievable trade-offs between its standard and robust accuracies.
Our proposed framework, Once-for-all Adversarial Training (OAT), is built on an innovative model-conditional training framework.
arXiv Detail & Related papers (2020-10-22T16:06:34Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.