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

11:00am - 12:30pn

Posters

  • 53- Duty of Care: A Call for Open and Responsible AI Innovation in Healthcare
  • 77- Predicting Variant Fitness of SARS-COV-2 from Full Viral Genome Sequences
  • 105- Toward Preventive Alzheimer’s Risk Screening via Cell-Subtype-Aware Brain-Blood Gene Modeling
  • 111- Conformal Risk Control for Semantic Uncertainty Quantification in Computed Tomography
  • 114- Adaptive Explanations via Direct Preference Optimization
  • 117- Conformal Prediction and Verification of Large Language Model Extractions in EHR Data
  • 121- Visual Gait Alignment for Sensorless Prostheses: Toward an Interpretable Digital Twin Framework
  • 125- One Pixel Can Change the Diagnosis: Adversarial and Non-Adversarial Robustness in Mammography
  • 126- Influence of Gender-Specific Data Imbalance in Parkinson’s Disease Classification
  • 129- Towards Personalized Explanations for Healthcare with Audit Trails
12:30pm -2:00pm

Lunch

2:00pm - 2:45pm

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

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

Break

4:00pm - 4:45pm

Dr. Claire Xu
4:45pm - 5:30pm

Panel Discussion

5:30pm - 6:30 pm

Poster Session

Nov 7

9:00am - 9:45am

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

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

Break

11:00am - 12:30pn

Posters

  • 130- Confidence Calibration in Large Language Models for Oncology Patients Using Temporal Models of Clinical Context Embeddings
  • 136- Understanding Accuracy but Unable to Identify Inaccuracy: Investigating the Effect of Conventional Knowledge Learning on Confidence Calibration of Large Language Models
  • 137- Diagnosing Dermoscopic Models: Disentangling Image Clues from Artifacts with Data Surgery
  • 140- Exploring Various Embedding Methods on Medical Coding
  • 141- Knowledge and Precision: Evaluating Question Format and Context Effects on LLMs
  • 142- Prior Prompt Registry: Tracking LLM Respondent Influences
  • 143- Densely Connected U-Net with a Focused Aggregation Dilated Block for Medical Image Segmentation
  • 146- Shard-Unlearn: A Sharded Elastic SGD Privacy-Preserving Unlearning Method
  • 147- Data-Aware Layer Assignment for Secure and Private Distributed ML
  • 149- From Bias to Breakdown: Benchmarking Failures in Algorithmic Fairness
12:30pm -2:00pm

Lunch

2:00pm - 2:45pm

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

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

Break

4:00pm - 4:45pm

Posters

  • 151- Towards Reliable Lung Cancer Prediction: A Hybrid Framework Integrating Classical and Deep Learning Models
  • 152- CORE-Coma: Deep Learning Framework for Coma Prognosis from Auditory Event-Related Potentials
  • 153- Temporal Concept Tracing: Making Deep Learning Outputs Interpretable and Actionable for ICU Acute Kidney Injury Prevention
  • 154- MedPerturbing LLMs: A Comparative Study of Toxicity, Prompt Tuning, and Jailbreaks in Medical QA
  • 155- Preventing Another Tessa: Modular Safety Middleware for Health-Adjacent AI Assistants
4:45pm - 5:30pm

Dr. Mehran Ghafari and Dr. Xiao Tian
5:30pm - 6:30 pm

Poster Session

Nov 8

9:00am - 9:45am

Dr. Reva Schwartz and Gabriella Waters
9:45am - 10:30am

Dr. Justin Wagner
10:30am - 11:00am

Break

11:00am - 12:30pn

Posters

  • 156- Evaluating Uncertainty in Deep Q-Network Ensembles for Trustworthy Anomaly Detection in Medical Imaging
  • 158- Filtered-ViT: A Robust Defense Against Multiple Adversarial Patch Attacks
  • 132- Efficient context retention in LLMs: an alternative to in-context memory
  • 145- Category-Aware Fine-Tuning and Cross-Age Transferability in Image Memorability Prediction
  • 157- Transfer Learning for Subject-Independent Sleep Deprivation Detection from Resting-State EEG
12:30pm -2:00pm

Conclusion of the Symposium