Enforcing Fundamental Relations via Adversarial Attacks on Input Parameter Correlations

• URL: http://arxiv.org/abs/2501.05588v1
• Date: Thu, 09 Jan 2025 21:45:09 GMT
• Title: Enforcing Fundamental Relations via Adversarial Attacks on Input Parameter Correlations
• Authors: Timo Saala, Lucie Flek, Alexander Jung, Akbar Karimi, Alexander Schmidt, Matthias Schott, Philipp Soldin, Christopher Wiebusch,
• Abstract summary: Correlations between input parameters play a crucial role in many scientific classification tasks. We present a new adversarial attack algorithm called Random Distribution Shuffle Attack (RDSA) We demonstrate the RDSA effectiveness on six classification tasks.
• Score: 76.2226569692207
• License:
• Abstract: Correlations between input parameters play a crucial role in many scientific classification tasks, since these are often related to fundamental laws of nature. For example, in high energy physics, one of the common deep learning use-cases is the classification of signal and background processes in particle collisions. In many such cases, the fundamental principles of the correlations between observables are often better understood than the actual distributions of the observables themselves. In this work, we present a new adversarial attack algorithm called Random Distribution Shuffle Attack (RDSA), emphasizing the correlations between observables in the network rather than individual feature characteristics. Correct application of the proposed novel attack can result in a significant improvement in classification performance - particularly in the context of data augmentation - when using the generated adversaries within adversarial training. Given that correlations between input features are also crucial in many other disciplines. We demonstrate the RDSA effectiveness on six classification tasks, including two particle collision challenges (using CERN Open Data), hand-written digit recognition (MNIST784), human activity recognition (HAR), weather forecasting (Rain in Australia), and ICU patient mortality (MIMIC-IV), demonstrating a general use case beyond fundamental physics for this new type of adversarial attack algorithms.

Related papers

• Learning Robust Classifiers with Self-Guided Spurious Correlation Mitigation [26.544938760265136]
  Deep neural classifiers rely on spurious correlations between spurious attributes of inputs and targets to make predictions. We propose a self-guided spurious correlation mitigation framework. We show that training the classifier to distinguish different prediction behaviors reduces its reliance on spurious correlations without knowing them a priori.
  arXiv  Detail & Related papers  (2024-05-06T17:12:21Z)
• How adversarial attacks can disrupt seemingly stable accurate classifiers [76.95145661711514]
  Adversarial attacks dramatically change the output of an otherwise accurate learning system using a seemingly inconsequential modification to a piece of input data. Here, we show that this may be seen as a fundamental feature of classifiers working with high dimensional input data. We introduce a simple generic and generalisable framework for which key behaviours observed in practical systems arise with high probability.
  arXiv  Detail & Related papers  (2023-09-07T12:02:00Z)
• Doubly Robust Instance-Reweighted Adversarial Training [107.40683655362285]
  We propose a novel doubly-robust instance reweighted adversarial framework. Our importance weights are obtained by optimizing the KL-divergence regularized loss function. Our proposed approach outperforms related state-of-the-art baseline methods in terms of average robust performance.
  arXiv  Detail & Related papers  (2023-08-01T06:16:18Z)
• Investigating Adversarial Vulnerability and Implicit Bias through Frequency Analysis [0.3985805843651649]
  In this work, we investigate the relation between these perturbations and the implicit bias of neural networks trained with gradient-based algorithms. We identify the minimal and most critical frequencies necessary for accurate classification or misclassification respectively for each input image and its adversarially perturbed version. Our results provide empirical evidence that the network bias in Fourier space and the target frequencies of adversarial attacks are highly correlated and suggest new potential strategies for adversarial defence.
  arXiv  Detail & Related papers  (2023-05-24T14:40:23Z)
• Counterfactual Adversarial Learning with Representation Interpolation [11.843735677432166]
  We introduce Counterfactual Adrial Training framework to tackle the problem from aversa causality perspective. Experiments demonstrate that CAT achieves substantial performance improvement over SOTA across different downstream tasks.
  arXiv  Detail & Related papers  (2021-09-10T09:23:08Z)
• ACP++: Action Co-occurrence Priors for Human-Object Interaction Detection [102.9428507180728]
  A common problem in the task of human-object interaction (HOI) detection is that numerous HOI classes have only a small number of labeled examples. We observe that there exist natural correlations and anti-correlations among human-object interactions. We present techniques to learn these priors and leverage them for more effective training, especially on rare classes.
  arXiv  Detail & Related papers  (2021-09-09T06:02:50Z)
• Vulnerability Under Adversarial Machine Learning: Bias or Variance? [77.30759061082085]
  We investigate the effect of adversarial machine learning on the bias and variance of a trained deep neural network. Our analysis sheds light on why the deep neural networks have poor performance under adversarial perturbation. We introduce a new adversarial machine learning algorithm with lower computational complexity than well-known adversarial machine learning strategies.
  arXiv  Detail & Related papers  (2020-08-01T00:58:54Z)
• Detecting Human-Object Interactions with Action Co-occurrence Priors [108.31956827512376]
  A common problem in human-object interaction (HOI) detection task is that numerous HOI classes have only a small number of labeled examples. We observe that there exist natural correlations and anti-correlations among human-object interactions. We present techniques to learn these priors and leverage them for more effective training, especially in rare classes.
  arXiv  Detail & Related papers  (2020-07-17T02:47:45Z)

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.