Adversarial flows: A gradient flow characterization of adversarial attacks

• URL: http://arxiv.org/abs/2406.05376v2
• Date: Tue, 11 Jun 2024 08:20:26 GMT
• Title: Adversarial flows: A gradient flow characterization of adversarial attacks
• Authors: Lukas Weigand, Tim Roith, Martin Burger,
• Abstract summary: A popular method to perform adversarial attacks on neuronal networks is the so-called fast gradient sign method. We show convergence of the discretization to the associated gradient flow.
• Score: 1.8749305679160366
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A popular method to perform adversarial attacks on neuronal networks is the so-called fast gradient sign method and its iterative variant. In this paper, we interpret this method as an explicit Euler discretization of a differential inclusion, where we also show convergence of the discretization to the associated gradient flow. To do so, we consider the concept of p-curves of maximal slope in the case $p=\infty$. We prove existence of $\infty$-curves of maximum slope and derive an alternative characterization via differential inclusions. Furthermore, we also consider Wasserstein gradient flows for potential energies, where we show that curves in the Wasserstein space can be characterized by a representing measure on the space of curves in the underlying Banach space, which fulfill the differential inclusion. The application of our theory to the finite-dimensional setting is twofold: On the one hand, we show that a whole class of normalized gradient descent methods (in particular signed gradient descent) converge, up to subsequences, to the flow, when sending the step size to zero. On the other hand, in the distributional setting, we show that the inner optimization task of adversarial training objective can be characterized via $\infty$-curves of maximum slope on an appropriate optimal transport space.

Related papers

• Adaptive Federated Learning Over the Air [108.62635460744109]
  We propose a federated version of adaptive gradient methods, particularly AdaGrad and Adam, within the framework of over-the-air model training. Our analysis shows that the AdaGrad-based training algorithm converges to a stationary point at the rate of $mathcalO( ln(T) / T 1 - frac1alpha ).
  arXiv  Detail & Related papers  (2024-03-11T09:10:37Z)
• Adaptive Step Sizes for Preconditioned Stochastic Gradient Descent [0.3831327965422187]
  This paper proposes a novel approach to adaptive step sizes in gradient descent (SGD) We use quantities that we have identified as numerically traceable -- the Lipschitz constant for gradients and a concept of the local variance in search directions.
  arXiv  Detail & Related papers  (2023-11-28T17:03:56Z)
• Stochastic Gradient Descent for Gaussian Processes Done Right [86.83678041846971]
  We show that when emphdone right -- by which we mean using specific insights from optimisation and kernel communities -- gradient descent is highly effective. We introduce a emphstochastic dual descent algorithm, explain its design in an intuitive manner and illustrate the design choices. Our method places Gaussian process regression on par with state-of-the-art graph neural networks for molecular binding affinity prediction.
  arXiv  Detail & Related papers  (2023-10-31T16:15:13Z)
• Bridging the Gap Between Variational Inference and Wasserstein Gradient Flows [6.452626686361619]
  We bridge the gap between variational inference and Wasserstein gradient flows. Under certain conditions, the Bures-Wasserstein gradient flow can be recast as the Euclidean gradient flow. We also offer an alternative perspective on the path-derivative gradient, framing it as a distillation procedure to the Wasserstein gradient flow.
  arXiv  Detail & Related papers  (2023-10-31T00:10:19Z)
• Particle-based Variational Inference with Generalized Wasserstein Gradient Flow [32.37056212527921]
  We propose a ParVI framework, called generalized Wasserstein gradient descent (GWG) We show that GWG exhibits strong convergence guarantees. We also provide an adaptive version that automatically chooses Wasserstein metric to accelerate convergence.
  arXiv  Detail & Related papers  (2023-10-25T10:05:42Z)
• Sampling via Gradient Flows in the Space of Probability Measures [10.892894776497165]
  Recent work shows that algorithms derived by considering gradient flows in the space of probability measures open up new avenues for algorithm development. This paper makes three contributions to this sampling approach by scrutinizing the design components of such gradient flows.
  arXiv  Detail & Related papers  (2023-10-05T15:20:35Z)
• Gradient Flows for Sampling: Mean-Field Models, Gaussian Approximations and Affine Invariance [10.153270126742369]
  We study gradient flows in both probability density space and Gaussian space. The flow in the Gaussian space may be understood as a Gaussian approximation of the flow.
  arXiv  Detail & Related papers  (2023-02-21T21:44:08Z)
• Differentiable Annealed Importance Sampling and the Perils of Gradient Noise [68.44523807580438]
  Annealed importance sampling (AIS) and related algorithms are highly effective tools for marginal likelihood estimation. Differentiability is a desirable property as it would admit the possibility of optimizing marginal likelihood as an objective. We propose a differentiable algorithm by abandoning Metropolis-Hastings steps, which further unlocks mini-batch computation.
  arXiv  Detail & Related papers  (2021-07-21T17:10:14Z)
• Large-Scale Wasserstein Gradient Flows [84.73670288608025]
  We introduce a scalable scheme to approximate Wasserstein gradient flows. Our approach relies on input neural networks (ICNNs) to discretize the JKO steps. As a result, we can sample from the measure at each step of the gradient diffusion and compute its density.
  arXiv  Detail & Related papers  (2021-06-01T19:21:48Z)
• Zeroth-Order Hybrid Gradient Descent: Towards A Principled Black-Box Optimization Framework [100.36569795440889]
  This work is on the iteration of zero-th-order (ZO) optimization which does not require first-order information. We show that with a graceful design in coordinate importance sampling, the proposed ZO optimization method is efficient both in terms of complexity as well as as function query cost.
  arXiv  Detail & Related papers  (2020-12-21T17:29:58Z)
• A Near-Optimal Gradient Flow for Learning Neural Energy-Based Models [93.24030378630175]
  We propose a novel numerical scheme to optimize the gradient flows for learning energy-based models (EBMs) We derive a second-order Wasserstein gradient flow of the global relative entropy from Fokker-Planck equation. Compared with existing schemes, Wasserstein gradient flow is a smoother and near-optimal numerical scheme to approximate real data densities.
  arXiv  Detail & Related papers  (2019-10-31T02:26:20Z)

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.