Haizhong Zheng

adversarial robustness (1) model robustness (1) adversarial training (1) structured sparsity (1) training efficiency (1) adversarial perturbation (1) adversarial example (1) inference efficiency (1) code agent (1) transferable adversarial example (1) activation sparsity (1) security vulnerability (1) neuron pruning (1) large language model (1) adversarial accuracy (1) information exposure (1) functionally correct patch (1)