SECURE-AI4H Banner

AAAI Fall Symposium – SECURE‑AI4H

Safe, Ethical, Certified, Uncertainty-aware, Robust, and Explainable AI

November 6 – 8, 2025

Westin Arlington Gateway, VA

Home Call for Papers Speakers Program Venue Registration

Schedule

Nov 6

9:00am - 9:45am

Dr. Aidon Zhang
9:45am - 10:30am

Dr. Gamze Gursoy
10:30am - 11:00am

Break

  • 121 — Visual Gait Alignment for Sensorless Prostheses: Toward an Interpretable Digital Twin Framework 11:00 - 11:10
  • 125- One Pixel Can Change the Diagnosis: Adversarial and Non-Adversarial Robustness in Mammography 11:10 - 11:20
  • 126- Influence of Gender-Specific Data Imbalance in Parkinson’s Disease Classification 11:20 - 11:30
  • 136- How Missing Medication Data Contributes to Bias in Alzheimer’s Disease Machine Learning Models 11:30 - 11:40
  • 142- Hermes: A Modular Multi-Agent System for Structuring Clinical Text 11:40 - 11:50
  • 143- Fine-Tuning Large Language Models for Structured Clinical Report Generation Using GRPO 11:50 - 12:00
  • 144- Embedding vs Image-Based AI: A Comparative Fairness Study in Chest X-ray Analysis 12:00 - 12:10
  • 148- C2BM: Causal Concept Disentanglement for Fair Multimodal COVID-19 Detection 12:10 - 12:20
  • 157- Transfer Learning for Subject-Independent Sleep Deprivation Detection from Resting-State EEG 12:20 - 12:30
12:30pm -2:00pm

Lunch + Poster Display

2:00pm - 2:45pm

Dr.Salamata Konate
2:45pm - 3:30pm

Dr. Gangqin Hu
3:30pm - 4:00pm

Break

  • 158- Filtered-ViT: A Robust Defense Against Multiple Adversarial Patch Attacks 4:00 - 4:10
  • 145- Category-Aware Fine-Tuning and Cross-Age Transferability in Image Memorability Prediction 4:10 - 4:20
4:20pm - 5:15pm

Panel Discussion

5:30pm - 6:30 pm

Opening Reception

Nov 7

9:00am - 9:45am

Dr. Qingyu Chen
9:45am - 10:30am

Dr. Apurv Ratan Murty
10:30am - 11:00am

Break

  • 77- Predicting Variant Fitness of SARS-COV-2 from Full Viral Genome Sequences 11:00 - 11:10
  • 111- Conformal Risk Control for Semantic Uncertainty Quantification in Computed Tomography 11:10 - 11:20
  • 130- Confidence Calibration in Large Language Models for Uncertainty Quantification: Affecting Calibration with Conditional Weight Updates 11:20 - 11:30
  • 140- Predicting Glucose Test Ordering in Hospitalized Patients Using Temporal Models of Clinical Context Embeddings 11:30 - 11:40
  • 129- Towards Personalized Explanations for Healthcare with Audit Trails 11:40 - 11:50
  • 146- Shard-Unlearn: A Sharded Elastic SGD Privacy Preserving Federated Unlearning Framework for 5G-assisted Healthcare 11:50 - 12:00
  • 147- Data-Aware Layer Assignment for Secure and Efficient Communication in Federated Learning for Medical Image Analysis 12:10 - 12:20
  • 149- From Bias to Breakdown: Benchmarking Failure Mode Analysis of Single-cell RNA Sequencing Foundation Models in Acute Myeloid Leukemia 12:20 - 12:30
  • 155- Preventing Another Tessa: Modular Safety Middleware for Health-Adjacent AI Assistants 12:30 - 12:40
12:40pm -2:00pm

Lunch

2:00pm - 2:45pm

Dr. Jonathan Takeshita
2:45pm - 3:30pm

Dr. Philippe Giabbanelli
3:30pm - 4:00pm

Break

  • 53- Duty of Care: A Call for Open and Responsible AI Innovation in Healthcare 4:00 - 4:10
  • 151- Towards Reliable Lung Cancer Prediction: A Hybrid Framework Integrating Classical and Deep Learning Models 4:10 - 4:20
  • 152- CORE-Coma: Deep Learning Framework for Coma Prognosis from Auditory Event-Related Potentials 4:20 - 4:30
  • 153- Temporal Concept Tracing: Making Deep Learning Outputs Interpretable and Actionable for ICU Acute Kidney Injury Prevention 4:30 - 4:40
  • 154- MedPerturbing LLMs: A Comparative Study of Toxicity, Prompt Tuning, and Jailbreaks in Medical QA 4:40 - 4:50
4:50pm - 6:30 pm

Poster Display

Nov 8

9:00am - 9:45am

Dr. Mohammad Iqbal Nouyed
9:45am - 10:30am

Dr. Meharn Ghafari and Dr. Xiao Tian
10:30am - 11:00am

Break

  • 105- Toward Preventive Alzheimer’s Risk Screening via Cell-Subtype-Aware Brain-Blood Gene Modeling 11:00 - 11:10
  • 114- Adaptive Explanations via Direct Preference Optimization 11:10 - 11:20
  • 117- Conformal Prediction and Verification of Large Language Model Extractions in EHR Data 11:20 - 11:30
  • 156- Evaluating Uncertainty in Deep Q-Network Ensembles for Trustworthy Anomaly Detection in Medical Imaging 11:30 - 11:40
  • 132- Efficient context retention in LLMs: an alternative to in-context memory 11:40 - 11:50
11:40am -12:00pm

Conclusion of the Symposium Followed by Lunch