5 papers
What the Eyes See, the LLMs Miss: Exploiting Human Perception for Adversarial Text Attacks
Qin Yang, Lu Malloy, Joshua Lee +4
Large language model (LLM)-powered content moderation systems are a critical defense against harmful online content. However, they operate primarily on tokenized text and often ove…
Lap2: Revisiting Laplace DP-SGD for High Dimensions via Majorization Theory
Meisam Mohammady, Qin Yang, Nicholas Stout +4
Differentially Private Stochastic Gradient Descent (DP-SGD) is a cornerstone technique for ensuring privacy in deep learning, widely used in both training from scratch and fine-tun…
PLRV-O: Advancing Differentially Private Deep Learning via Privacy Loss Random Variable Optimization
Qin Yang, Nicholas Stout, Meisam Mohammady +6
Differentially Private Stochastic Gradient Descent (DP-SGD) is a standard method for enforcing privacy in deep learning, typically using the Gaussian mechanism to perturb gradient…
Universally Harmonizing Differential Privacy Mechanisms for Federated Learning: Boosting Accuracy and Convergence
Shuya Feng, Meisam Mohammady, Hanbin Hong +4
Differentially private federated learning (DP-FL) is a promising technique for collaborative model training while ensuring provable privacy for clients. However, optimizing the tra…
LMO-DP: Optimizing the Randomization Mechanism for Differentially Private Fine-Tuning (Large) Language Models
Qin Yang, Meisam Mohammad, Han Wang +5
Differentially Private Stochastic Gradient Descent (DP-SGD) and its variants have been proposed to ensure rigorous privacy for fine-tuning large-scale pre-trained language models.…