Search Results for author:
Found 7 papers, 4 papers with code
Defense Against Adversarial Attacks via Controlling Gradient Leaking on Embedded Manifolds
Based on our investigation, we further present a new robust learning algorithm which encourages a larger gradient component in the tangent space of data manifold, suppressing the gradient leaking phenomenon consequently.
Query-Efficient Black-box Adversarial Attacks Guided by a Transfer-based Prior
However, the existing methods inevitably suffer from low attack success rates or poor query efficiency since it is difficult to estimate the gradient in a high-dimensional input space with limited information.
On the Convergence of Prior-Guided Zeroth-Order Optimization Algorithms
Finally, our theoretical results are confirmed by experiments on several numerical benchmarks as well as adversarial attacks.
Switching Transferable Gradient Directions for Query-Efficient Black-Box Adversarial Attacks
In each iteration, SWITCH first tries to update the current sample along the direction of $\hat{\mathbf{g}}$, but considers switching to its opposite direction $-\hat{\mathbf{g}}$ if our algorithm detects that it does not increase the value of the attack objective function.
A Wasserstein Minimum Velocity Approach to Learning Unnormalized Models
Score matching provides an effective approach to learning flexible unnormalized models, but its scalability is limited by the need to evaluate a second-order derivative.
Improving Black-box Adversarial Attacks with a Transfer-based Prior
We consider the black-box adversarial setting, where the adversary has to generate adversarial perturbations without access to the target models to compute gradients.
Stochastic Gradient Hamiltonian Monte Carlo with Variance Reduction for Bayesian Inference
In this paper, we apply the variance reduction tricks on Hamiltonian Monte Carlo and achieve better theoretical convergence results compared with the variance-reduced Langevin dynamics.
