3 papers
cs.CR2026
Privacy Enhanced PEFT: Tensor Train Decomposition Improves Privacy Utility Tradeoffs under DP-SGD
Pradip Kunwar, Minh Vu, Maanak Gupta +1
Fine-tuning large language models on sensitive data poses significant privacy risks, as membership inference attacks can reveal whether individual records were used during training…
cs.LG2025
TT-LoRA MoE: Unifying Parameter-Efficient Fine-Tuning and Sparse Mixture-of-Experts
Pradip Kunwar, Minh N. Vu, Maanak Gupta +2
We propose Tensor-Trained Low-Rank Adaptation Mixture of Experts (TT-LoRA MoE), a novel computational framework integrating Parameter-Efficient Fine-Tuning (PEFT) with sparse MoE r…
cs.CR2025
SoK: Leveraging Transformers for Malware Analysis
Pradip Kunwar, Kshitiz Aryal, Maanak Gupta +2
The introduction of transformers has been an important breakthrough for AI research and application as transformers are the foundation behind Generative AI. A promising application…