Improving Adversarial Robustness of DEQs with Explicit Regulations Along the Neural Dynamics

• URL: http://arxiv.org/abs/2306.01435v1
• Date: Fri, 2 Jun 2023 10:49:35 GMT
• Title: Improving Adversarial Robustness of DEQs with Explicit Regulations Along the Neural Dynamics
• Authors: Zonghan Yang, Peng Li, Tianyu Pang, Yang Liu
• Abstract summary: Deep equilibrium (DEQ) models replace the multiple-layer stacking of conventional deep networks with a fixed-point iteration of a single-layer transformation. Existing works improve the robustness of general DEQ models with the widely-used adversarial training (AT) framework, but they fail to exploit the structural uniquenesses of DEQ models. We propose reducing prediction entropy by progressively updating inputs along the neural dynamics. Our methods substantially increase the robustness of DEQ models and even outperform the strong deep network baselines.
• Score: 26.94367957377311
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep equilibrium (DEQ) models replace the multiple-layer stacking of conventional deep networks with a fixed-point iteration of a single-layer transformation. Having been demonstrated to be competitive in a variety of real-world scenarios, the adversarial robustness of general DEQs becomes increasingly crucial for their reliable deployment. Existing works improve the robustness of general DEQ models with the widely-used adversarial training (AT) framework, but they fail to exploit the structural uniquenesses of DEQ models. To this end, we interpret DEQs through the lens of neural dynamics and find that AT under-regulates intermediate states. Besides, the intermediate states typically provide predictions with a high prediction entropy. Informed by the correlation between the entropy of dynamical systems and their stability properties, we propose reducing prediction entropy by progressively updating inputs along the neural dynamics. During AT, we also utilize random intermediate states to compute the loss function. Our methods regulate the neural dynamics of DEQ models in this manner. Extensive experiments demonstrate that our methods substantially increase the robustness of DEQ models and even outperform the strong deep network baselines.

Related papers

• A short trajectory is all you need: A transformer-based model for long-time dissipative quantum dynamics [0.0]
  We show that a deep artificial neural network can predict the long-time population dynamics of a quantum system coupled to a dissipative environment. Our model is more accurate than classical forecasting models, such as recurrent neural networks.
  arXiv  Detail & Related papers  (2024-09-17T16:17:52Z)
• Learning Neural Constitutive Laws From Motion Observations for Generalizable PDE Dynamics [97.38308257547186]
  Many NN approaches learn an end-to-end model that implicitly models both the governing PDE and material models. We argue that the governing PDEs are often well-known and should be explicitly enforced rather than learned. We introduce a new framework termed "Neural Constitutive Laws" (NCLaw) which utilizes a network architecture that strictly guarantees standard priors.
  arXiv  Detail & Related papers  (2023-04-27T17:42:24Z)
• ConCerNet: A Contrastive Learning Based Framework for Automated Conservation Law Discovery and Trustworthy Dynamical System Prediction [82.81767856234956]
  This paper proposes a new learning framework named ConCerNet to improve the trustworthiness of the DNN based dynamics modeling. We show that our method consistently outperforms the baseline neural networks in both coordinate error and conservation metrics.
  arXiv  Detail & Related papers  (2023-02-11T21:07:30Z)
• Expressive architectures enhance interpretability of dynamics-based neural population models [2.294014185517203]
  We evaluate the performance of sequential autoencoders (SAEs) in recovering latent chaotic attractors from simulated neural datasets. We found that SAEs with widely-used recurrent neural network (RNN)-based dynamics were unable to infer accurate firing rates at the true latent state dimensionality.
  arXiv  Detail & Related papers  (2022-12-07T16:44:26Z)
• Physics Informed Neural Network for Dynamic Stress Prediction [10.588266927411434]
  A Physics Informed Neural Network (PINN) model is proposed to predict the entire sequence of stress distribution based on Finite Element simulations. Using automatic differentiation, we embed a PDE into a deep neural network's loss function to incorporate information from measurements and PDEs. The PINN-Stress model can predict the sequence of stress distribution in almost real-time and can generalize better than the model without PINN.
  arXiv  Detail & Related papers  (2022-11-28T16:03:21Z)
• Dynamics with autoregressive neural quantum states: application to critical quench dynamics [41.94295877935867]
  We present an alternative general scheme that enables one to capture long-time dynamics of quantum systems in a stable fashion. We apply the scheme to time-dependent quench dynamics by investigating the Kibble-Zurek mechanism in the two-dimensional quantum Ising model.
  arXiv  Detail & Related papers  (2022-09-07T15:50:00Z)
• Disentangled Generative Models for Robust Prediction of System Dynamics [2.6424064030995957]
  In this work, we treat the domain parameters of dynamical systems as factors of variation of the data generating process. By leveraging ideas from supervised disentanglement and causal factorization, we aim to separate the domain parameters from the dynamics in the latent space of generative models. Results indicate that disentangled VAEs adapt better to domain parameters spaces that were not present in the training data.
  arXiv  Detail & Related papers  (2021-08-26T09:58:06Z)
• Stabilizing Equilibrium Models by Jacobian Regularization [151.78151873928027]
  Deep equilibrium networks (DEQs) are a new class of models that eschews traditional depth in favor of finding the fixed point of a single nonlinear layer. We propose a regularization scheme for DEQ models that explicitly regularizes the Jacobian of the fixed-point update equations to stabilize the learning of equilibrium models. We show that this regularization adds only minimal computational cost, significantly stabilizes the fixed-point convergence in both forward and backward passes, and scales well to high-dimensional, realistic domains.
  arXiv  Detail & Related papers  (2021-06-28T00:14:11Z)
• Non-Singular Adversarial Robustness of Neural Networks [58.731070632586594]
  Adrial robustness has become an emerging challenge for neural network owing to its over-sensitivity to small input perturbations. We formalize the notion of non-singular adversarial robustness for neural networks through the lens of joint perturbations to data inputs as well as model weights.
  arXiv  Detail & Related papers  (2021-02-23T20:59:30Z)
• Neural Networks with Recurrent Generative Feedback [61.90658210112138]
  We instantiate this design on convolutional neural networks (CNNs) In the experiments, CNN-F shows considerably improved adversarial robustness over conventional feedforward CNNs on standard benchmarks.
  arXiv  Detail & Related papers  (2020-07-17T19:32:48Z)
• An Ode to an ODE [78.97367880223254]
  We present a new paradigm for Neural ODE algorithms, called ODEtoODE, where time-dependent parameters of the main flow evolve according to a matrix flow on the group O(d) This nested system of two flows provides stability and effectiveness of training and provably solves the gradient vanishing-explosion problem.
  arXiv  Detail & Related papers  (2020-06-19T22:05:19Z)

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.