Xiaohui Kuang

large language model (2) code vulnerability detection (2) safety evaluation (2) adversarial testing (2) black-box attack (2) red teaming (2) semantic alignment (1) nearest neighbor (1) monte carlo tree search (1) adversarial attack (1) adversarial perturbation (1) adversarial example (1) vulnerability detection (1) discriminative representation (1) gradient-based attack (1) cross-domain transfer (1) test case generation (1) decision-based attack (1) neural network vulnerability (1) knowledge fusion (1)