Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
CogniVault: Enabling Privacy-Aware Cognitive Distortion Detection in Intelligent Mental Health Applications
Mental health applications are increasingly leveraging intelligent systems to sup- port psychological well-being, yet preserving user privacy remains a major concern. This thesis presents CogniVault, a secure ecosystem for cognitive distortion data. The framework includes Cognify, a mobile journalin...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
AUC Knowledge Fountain
2026
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| Summary: | Mental health applications are increasingly leveraging intelligent systems to sup- port psychological well-being, yet preserving user privacy remains a major concern. This thesis presents CogniVault, a secure ecosystem for cognitive distortion data. The framework includes Cognify, a mobile journaling application that detects cog- nitive distortions in user-written journal entries using a locally deployed machine learning model. Cognitive distortions are maladaptive thought patterns such as catastrophizing or personalization, which the app identifies to provide therapeu- tic insights. To ensure privacy-preserving data analytics, CogniVault includes the design and implementation of a hybrid security architecture, PRISM-HDI, that combines Paillier Homomorphic Encryption (HE), Differential Privacy (DP), and Immutability. User data, including mood scores and detected cognitive distortion labels, are encrypted on-device using Paillier HE and sent to a secure backend where encrypted aggregation is performed. After decryption, noise is added ac- cording to differential privacy guarantees to protect individual user contributions before presenting insights to therapists and other users. These insights include label and mood distribution across patients and per-user temporal trends. To protect the safety of stored data on the cloud, we implement blockchain inspired immutability to ensure data is tamper-proof. We evaluate the system’s usabil- ity, encryption overhead, and security resilience to demonstrate its feasibility for real-world deployment. Our results show that privacy can be preserved without significantly affecting performance or sacrificing the utility of mental health ana- lytics, paving the way for responsible AI in mental health care. |
|---|