DS
Dumindu Samaraweera
cs.AIcs.CRcs.LGcs.CVcs.SE
On Valency
published · living versionsW_hunckn5r·v1 · currentpublished
The Privacy and Security Risks of Edge LLM Optimization
with Mingchen Li, Ren-Yi Huang, Prashant Shekhar, J. Morris Chang
1 version
Preprints & journals
6 papers in the corpus · 2025–2026Securing LLMs in the Wild: Privacy and Security Challenges at the Edge2607.13088v1 · Ren-Yi Huang, Mingchen Li, Dumindu Samaraweera et al.2026 · 0 citationsarXiv
Building Trust in the Skies: A Knowledge-Grounded LLM-based Framework for Aviation Safety2604.13101v1 · Anirudh Iyengar, Alisa Tiselska, Dumindu Samaraweera et al.2026 · 3 citationsarXiv
Advancing Practical Homomorphic Encryption for Federated Learning: Theoretical Guarantees and Efficiency Optimizations2509.20476v1 · Ren-Yi Huang, Dumindu Samaraweera, Prashant Shekhar et al.2025 · 0 citationsarXiv
Secure Distributed Learning for CAVs: Defending Against Gradient Leakage with Leveled Homomorphic Encryption2506.07894v1 · Muhammad Ali Najjar, Ren-Yi Huang, Dumindu Samaraweera et al.2025 · 0 citationsarXiv
Exploiting Meta-Learning-based Poisoning Attacks for Graph Link Prediction2504.06492v2 · Mingchen Li, Di Zhuang, Keyu Chen et al.2025 · 0 citationsarXiv
Cross-Model Transferability of Adversarial Patches in Real-time Segmentation for Autonomous Driving2502.16012v1 · Prashant Shekhar, Bidur Devkota, Dumindu Samaraweera et al.2025 · 0 citationsarXiv
Career total: 20 works. 6 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.