Pengfei He

Privacy (1)

large language model (9) multi-agent system (3) retrieval-augmented generation (3) training datum (2) domain adaptation (2) language model (2) adversarial attack (2) few-shot learning (1) adversarial robustness (1) privacy attack (1) sparse coding (1) text classification (1) gradient-based optimization (1) uncertainty quantification (1) graph laplacian (1) adversarial learning (1) privacy preservation (1) chain-of-thought reasoning (1) adversarial training (1) manifold learning (1)