Variational Randomized Smoothing for Sample-Wise Adversarial Robustness

• URL: http://arxiv.org/abs/2407.11844v1
• Date: Tue, 16 Jul 2024 15:25:13 GMT
• Title: Variational Randomized Smoothing for Sample-Wise Adversarial Robustness
• Authors: Ryo Hase, Ye Wang, Toshiaki Koike-Akino, Jing Liu, Kieran Parsons,
• Abstract summary: This paper proposes a new variational framework that uses a per-sample noise level suitable for each input by introducing a noise level selector. Our experimental results demonstrate enhancement of empirical robustness against adversarial attacks.
• Score: 12.455543308060196
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Randomized smoothing is a defensive technique to achieve enhanced robustness against adversarial examples which are small input perturbations that degrade the performance of neural network models. Conventional randomized smoothing adds random noise with a fixed noise level for every input sample to smooth out adversarial perturbations. This paper proposes a new variational framework that uses a per-sample noise level suitable for each input by introducing a noise level selector. Our experimental results demonstrate enhancement of empirical robustness against adversarial attacks. We also provide and analyze the certified robustness for our sample-wise smoothing method.

Related papers

• Large Language Model Enhanced Hard Sample Identification for Denoising Recommendation [4.297249011611168]
  Implicit feedback is often used to build recommender systems. Previous studies have attempted to alleviate this by identifying noisy samples based on their diverged patterns. We propose a Large Language Model Enhanced Hard Sample Denoising framework.
  arXiv  Detail & Related papers  (2024-09-16T14:57:09Z)
• ROPO: Robust Preference Optimization for Large Language Models [59.10763211091664]
  We propose an iterative alignment approach that integrates noise-tolerance and filtering of noisy samples without the aid of external models. Experiments on three widely-used datasets with Mistral-7B and Llama-2-7B demonstrate that ROPO significantly outperforms existing preference alignment methods.
  arXiv  Detail & Related papers  (2024-04-05T13:58:51Z)
• Accelerated Smoothing: A Scalable Approach to Randomized Smoothing [4.530339602471495]
  We propose a novel approach that replaces Monte Carlo sampling with the training of a surrogate neural network. We show that our approach significantly accelerates the robust radius certification process, providing nearly $600$X improvement in time.
  arXiv  Detail & Related papers  (2024-02-12T09:07:54Z)
• May the Noise be with you: Adversarial Training without Adversarial Examples [3.4673556247932225]
  We investigate the question: Can we obtain adversarially-trained models without training on adversarial? Our proposed approach incorporates inherentity by embedding Gaussian noise within the layers of the NN model at training time. Our work contributes adversarially trained networks using a completely different approach, with empirically similar robustness to adversarial training.
  arXiv  Detail & Related papers  (2023-12-12T08:22:28Z)
• Improve Noise Tolerance of Robust Loss via Noise-Awareness [60.34670515595074]
  We propose a meta-learning method which is capable of adaptively learning a hyper parameter prediction function, called Noise-Aware-Robust-Loss-Adjuster (NARL-Adjuster for brevity) Four SOTA robust loss functions are attempted to be integrated with our algorithm, and comprehensive experiments substantiate the general availability and effectiveness of the proposed method in both its noise tolerance and performance.
  arXiv  Detail & Related papers  (2023-01-18T04:54:58Z)
• Confidence-aware Training of Smoothed Classifiers for Certified Robustness [75.95332266383417]
  We use "accuracy under Gaussian noise" as an easy-to-compute proxy of adversarial robustness for an input. Our experiments show that the proposed method consistently exhibits improved certified robustness upon state-of-the-art training methods.
  arXiv  Detail & Related papers  (2022-12-18T03:57:12Z)
• SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness [61.212486108346695]
  We propose a training scheme, coined SmoothMix, to control the robustness of smoothed classifiers via self-mixup. The proposed procedure effectively identifies over-confident, near off-class samples as a cause of limited robustness. Our experimental results demonstrate that the proposed method can significantly improve the certified $ell$-robustness of smoothed classifiers.
  arXiv  Detail & Related papers  (2021-11-17T18:20:59Z)
• Jo-SRC: A Contrastive Approach for Combating Noisy Labels [58.867237220886885]
  We propose a noise-robust approach named Jo-SRC (Joint Sample Selection and Model Regularization based on Consistency) Specifically, we train the network in a contrastive learning manner. Predictions from two different views of each sample are used to estimate its "likelihood" of being clean or out-of-distribution.
  arXiv  Detail & Related papers  (2021-03-24T07:26:07Z)
• Improved, Deterministic Smoothing for L1 Certified Robustness [119.86676998327864]
  We propose a non-additive and deterministic smoothing method, Deterministic Smoothing with Splitting Noise (DSSN) In contrast to uniform additive smoothing, the SSN certification does not require the random noise components used to be independent. This is the first work to provide deterministic "randomized smoothing" for a norm-based adversarial threat model.
  arXiv  Detail & Related papers  (2021-03-17T21:49:53Z)

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.