Related papers: Certified Training for Convolutional Perturbations

Certified Training for Convolutional Perturbations

URL: http://arxiv.org/abs/2607.18195v1
Date: Mon, 20 Jul 2026 17:36:05 GMT
Title: Certified Training for Convolutional Perturbations
Abstract summary: Vision models are susceptible to perturbations such as motion blur induced at runtime by a shaking camera.<n>We introduce a novel Certified Training approach that leverages an efficient encoding of convolutional perturbations to train provably robust models.
Score: 19.78125519648258
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
Abstract: Vision models have been found to be susceptible to perturbations such as motion blur induced at runtime by a shaking camera. This impedes their deployment in critical applications since phenomena such as slightly blurred vision might lead to failures, for example an object detector missing objects. While methods such as data augmentation or Adversarial Training can improve empirical robustness, they lack formal safety guarantees, making it difficult to identify and mitigate hidden vulnerabilities. We introduce a novel Certified Training approach that leverages an efficient encoding of convolutional perturbations to train provably robust models. Our method significantly outperforms Adversarial Training, achieving, for example, over 80% robust accuracy against motion blur of reasonable intensity on CIFAR10 while maintaining comparable standard accuracy.

Related papers

ARMOR: Manifold-Oriented Training for Adversarially Robust Aerial Object Detection under Data Scarcity [29.552503716131568]
We propose Adversarial Robustness with Manifold-Oriented Training (ARMOR) to tackle model vulnerability and training data scarcity.<n>ARMOR realizes the core insights of on-manifold adversarial training (OMAT) in low-data regimes.<n>ARMOR maintains strong clean performance of over 0.90 model confidence, while improving adversarial robustness by up to 0.32 in model confidence over state-of-the-art defenses.
arXiv Detail & Related papers (2026-08-30T02:14:40Z)
A Validation Strategy for Deep Learning Models: Evaluating and Enhancing Robustness [0.8532585403388676]
We propose a validation approach that extracts "weak robust" samples directly from the training dataset via local analysis.<n>These samples, being the most susceptible to perturbations, serve as an early and sensitive indicator of the model's vulnerabilities.<n>We demonstrate the effectiveness of our approach on models trained with CIFAR-10, CIFAR-100, and ImageNet.
arXiv Detail & Related papers (2025-09-23T16:14:14Z)
Confidence-aware Denoised Fine-tuning of Off-the-shelf Models for Certified Robustness [56.2479170374811]
We introduce Fine-Tuning with Confidence-Aware Denoised Image Selection (FT-CADIS) FT-CADIS is inspired by the observation that the confidence of off-the-shelf classifiers can effectively identify hallucinated images during denoised smoothing. It has established the state-of-the-art certified robustness among denoised smoothing methods across all $ell$-adversary radius in various benchmarks.
arXiv Detail & Related papers (2024-11-13T09:13:20Z)
A Hybrid Defense Strategy for Boosting Adversarial Robustness in Vision-Language Models [9.304845676825584]
We propose a novel adversarial training framework that integrates multiple attack strategies and advanced machine learning techniques. Experiments conducted on real-world datasets, including CIFAR-10 and CIFAR-100, demonstrate that the proposed method significantly enhances model robustness.
arXiv Detail & Related papers (2024-10-18T23:47:46Z)
Extreme Miscalibration and the Illusion of Adversarial Robustness [66.29268991629085]
Adversarial Training is often used to increase model robustness. We show that this observed gain in robustness is an illusion of robustness (IOR) We urge the NLP community to incorporate test-time temperature scaling into their robustness evaluations.
arXiv Detail & Related papers (2024-02-27T13:49:12Z)
Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck [77.37409441129995]
In practical scenarios where training data is limited, many predictive signals in the data can be rather from some biases in data acquisition. We consider an adversarial threat model under a mutual information constraint to cover a wider class of perturbations in training. We propose an autoencoder-based training to implement the objective, as well as practical encoder designs to facilitate the proposed hybrid discriminative-generative training.
arXiv Detail & Related papers (2023-03-24T16:03:21Z)
Adversarially-Aware Robust Object Detector [85.10894272034135]
We propose a Robust Detector (RobustDet) based on adversarially-aware convolution to disentangle gradients for model learning on clean and adversarial images. Our model effectively disentangles gradients and significantly enhances the detection robustness with maintaining the detection ability on clean images.
arXiv Detail & Related papers (2022-07-13T13:59:59Z)
Enhancing Adversarial Robustness for Deep Metric Learning [77.75152218980605]
adversarial robustness of deep metric learning models has to be improved. In order to avoid model collapse due to excessively hard examples, the existing defenses dismiss the min-max adversarial training. We propose Hardness Manipulation to efficiently perturb the training triplet till a specified level of hardness for adversarial training.
arXiv Detail & Related papers (2022-03-02T22:27:44Z)
Robust Pre-Training by Adversarial Contrastive Learning [120.33706897927391]
Recent work has shown that, when integrated with adversarial training, self-supervised pre-training can lead to state-of-the-art robustness. We improve robustness-aware self-supervised pre-training by learning representations consistent under both data augmentations and adversarial perturbations.
arXiv Detail & Related papers (2020-10-26T04:44:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.