Shagufta Mehnaz

semantic similarity (2) adversarial robustness (2) text classification (1) chain-of-thought reasoning (1) machine unlearning (1) privacy leakage (1) membership inference (1) jailbreak defense (1) pretrained language model (1) zero-shot performance (1) toxicity mitigation (1) large language model (1) adversarial text generation (1) data extraction attack (1) adversarial example attack (1) reinforcement learning (1) inference-time defense (1) natural language processing (1)