Towards Privacy-aware Mental Health AI Models: Advances, Challenges, and Opportunities
Not on the map. Why?
Abstract (arXiv)
Mental health disorders create profound personal and societal burdens, yet conventional diagnostics are resource-intensive and limit accessibility. Advances in artificial intelligence, particularly natural language processing and multimodal methods, offer promise for detecting and addressing mental disorders, but raise critical privacy risks. This paper examines these challenges and proposes solutions, including anonymization, synthetic data, and privacy-preserving training, while outlining frameworks for privacy-utility trade-offs, aiming to advance reliable, privacy-aware AI tools that support clinical decision-making and improve mental health outcomes.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 68 of its 134 references that are in the map. First posted on arXiv 1 Feb 2025.
Builds on
68 of 134 references.
References · 68
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
- 2016Deep Learning with Differential Privacycited by 2,682
- 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
- 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
- 2023NExT-GPT: Any-to-Any Multimodal LLMcited by 610
- 2021Differentially Private Fine-tuning of Language Modelscited by 392
- 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
- 2020DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detectioncited by 231
- 2024Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMscited by 224
- 2020Information Leakage in Embedding Modelscited by 199
38 more
- 2021FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Datasetcited by 179
- 2025MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMscited by 171
- 2015Inverting Visual Representations with Convolutional Networkscited by 168
- 2023DeID-GPT: Zero-shot Medical Text De-Identification by GPT-4cited by 128
- 2021When the Curious Abandon Honesty: Federated Learning Is Not Privatecited by 126
- 2023SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversationscited by 109
- 2022Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipecited by 108
- 2021LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognitioncited by 92
- 2024On Protecting the Data Privacy of Large Language Models (LLMs): A Surveycited by 91
- 2016De-identification of Patient Notes with Recurrent Neural Networkscited by 88
- 2024CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counselingcited by 88
- 2021Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forwardcited by 82
- 2024From Audio to Photoreal Embodiment: Synthesizing Humans in Conversationscited by 82
- 20223D face reconstruction with dense landmarkscited by 70
- 2017On the Reconstruction of Face Images from Deep Face Templatescited by 66
- 2020LDP-FL: Practical Private Aggregation in Federated Learning with Local Differential Privacycited by 63
- 2024Cactus: Towards Psychological Counseling Conversations using Cognitive Behavioral Theorycited by 60
- 2022Differentially Private Bias-Term Fine-tuning of Foundation Modelscited by 47
- 2020Differentially Private Language Models Benefit from Public Pre-trainingcited by 46
- 2023SMILE: Single-turn to Multi-turn Inclusive Language Expansion via ChatGPT for Mental Health Supportcited by 46
- 2021Data Poisoning Won't Save You From Facial Recognitioncited by 45
- 2024Interactive Agents: Simulating Counselor-Client Psychological Counseling via Role-Playing LLM-to-LLM Interactionscited by 43
- 2024ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesiscited by 41
- 2024The VoicePrivacy 2024 Challenge Evaluation Plancited by 39
- 2022Cocktail Party Attack: Breaking Aggregation-Based Privacy in Federated Learning using Independent Component Analysiscited by 29
- 2021Benchmarking Differential Privacy and Federated Learning for BERT Modelscited by 28
- 2020Face-Off: Adversarial Face Obfuscationcited by 25
- 2021IdentityDP: Differential Private Identification Protection for Face Imagescited by 24
- 2021CAPE: Context-Aware Private Embeddings for Private Language Learningcited by 22
- 2023Speaker anonymization using orthogonal Householder neural networkcited by 18
- 2024The VoicePrivacy 2022 Challenge: Progress and Perspectives in Voice Anonymisationcited by 17
- 2022Differentially Private Speaker Anonymizationcited by 16
- 2019Audio De-identification: A New Entity Recognition Taskcited by 14
- 2020PHICON: Improving Generalization of Clinical Text De-identification Models via Data Augmentationcited by 14
- 2020FoggySight: A Scheme for Facial Lookup Privacycited by 12
- 2023Efficient Explainable Face Verification based on Similarity Score Argument Backpropagationcited by 12
- 2023FIVA: Facial Image and Video Anonymization and Anonymization Defensecited by 12
- 2022Unsupervised Text Deidentificationcited by 11
50 most cited of 68 All 68 (JSON)
Built on by
Citing papers per year: 2025: 2.
2 papers.