1 citations · 1 across the 8 of their papers we have counts for
10 papers
MoE Router-Guided Clustering for Heterogeneous Federated Instruction Tuning
Ankita Sharma, Bahar Farahani, Sanaz Rahimi Moosavi +3
Federated instruction fine-tuning enables Large Language Models (LLMs) to adapt to decentralized, privacy-sensitive data without requiring data sharing. Recent Mixture-of-Experts (…
Membership Inference Attacks Expose Participation Privacy in ECG Foundation Encoders
Ziyu Wang, Elahe Khatibi, Ankita Sharma +4
Foundation-style ECG encoders pretrained with self-supervised learning are increasingly reused across tasks, institutions, and deployment contexts, often through model-as-a-service…
CARE-ECG: Causal Agent-based Reasoning for Explainable and Counterfactual ECG Interpretation
Elahe Khatibi, Ziyu Wang, Ankita Sharma +4
Large language models (LLMs) enable waveform-to-text ECG interpretation and interactive clinical questioning, yet most ECG-LLM systems still rely on weak signal-text alignment and…
Exploration of Low-Power Flexible Stress Monitoring Classifiers for Conformal Wearables
Florentia Afentaki, Sri Sai Rakesh Nakkilla, Konstantinos Balaskas +6
Conventional stress monitoring relies on episodic, symptom-focused interventions, missing the need for continuous, accessible, and cost-efficient solutions. State-of-the-art approa…
Linkage Attacks Expose Identity Risks in Public ECG Data Sharing
Ziyu Wang, Elahe Khatibi, Farshad Firouzi +3
The increasing availability of publicly shared electrocardiogram (ECG) data raises critical privacy concerns, as its biometric properties make individuals vulnerable to linkage att…
Defending Against Gradient Inversion Attacks for Biomedical Images via Learnable Data Perturbation
Shiyi Jiang, Farshad Firouzi, Krishnendu Chakrabarty
The increasing need for sharing healthcare data and collaborating on clinical research has raised privacy concerns. Health information leakage due to malicious attacks can lead to…
H3PIMAP: A Heterogeneity-Aware Multi-Objective DNN Mapping Framework on Electronic-Photonic Processing-in-Memory Architectures
Ziang Yin, Aashish Poonia, Ashish Reddy Bommana +7
The future of artificial intelligence (AI) acceleration demands a paradigm shift beyond the limitations of purely electronic or photonic architectures. Photonic analog computing de…
FLARE: Fault Attack Leveraging Address Reconfiguration Exploits in Multi-Tenant FPGAs
Jayeeta Chaudhuri, Hassan Nassar, Dennis R. E. Gnad +3
Modern FPGAs are increasingly supporting multi-tenancy to enable dynamic reconfiguration of user modules. While multi-tenant FPGAs improve utilization and flexibility, this paradig…
Hacking the Fabric: Targeting Partial Reconfiguration for Fault Injection in FPGA Fabrics
Jayeeta Chaudhuri, Hassan Nassar, Dennis R. E. Gnad +3
FPGAs are now ubiquitous in cloud computing infrastructures and reconfigurable system-on-chip, particularly for AI acceleration. Major cloud service providers such as Amazon and Mi…
SPICED: Syntactical Bug and Trojan Pattern Identification in A/MS Circuits using LLM-Enhanced Detection
Jayeeta Chaudhuri, Dhruv Thapar, Arjun Chaudhuri +2
Analog and mixed-signal (A/MS) integrated circuits (ICs) are crucial in modern electronics, playing key roles in signal processing, amplification, sensing, and power management. Ma…