← Search

Huosheng Xu

2 accepted papers

2025

Boosting Adversarial Transferability via Negative Hessian Trace Regularization

ICCV 2025poster

Transferability makes the black-box attacks to be practical. Recent studies demonstrate that adversarial examples situated at the flat maxima on the loss landscape tend to exhibit higher transferability and propose effective strategies to optimize adversarial examples to converge toward that region.…

Cited by 0SourcePDFScholar
2024

Reparameterized Importance Sampling for Robust Variational Bayesian Neural Networks

ICML 2024poster

Mean-field variational inference (MFVI) methods provide computationally cheap approximations to the posterior of Bayesian Neural Networks (BNNs) when compared to alternatives like MCMC. However, applying MFVI to BNNs encounters limitations due to the Monte Carlo sampling problem. This problem stems…

Cited by 0SourcePDFScholar