References

This page contains a collection of resources and references related to the AI Privacy publication for readers to further explore the topic.

1. AgenTRIM: Tool Risk Mitigation for Agentic AI
2. Analyzing Leakage of Personally Identifiable Information in Language Models
3. Beyond Latency: A System-Level Characterization of MPC and FHE for PPML
4. Beyond Memorization: Violating Privacy Via Inference with Large Language Models
5. Confidential Computing: Hardware-Based Trusted Execution for Applications and Data
6. De-Anonymizing Users across Rating Datasets via Record Linkage and Quasi-Identifier Attacks
7. Deep Learning with Differential Privacy
8. Efficient Differentially Private Secure Aggregation for Federated Learning via Hardness of Learning with Errors
9. Exploring Model Inversion Attacks in the Black-box Setting
10. Extracting Targeted Training Data from ASR Models, and How to Mitigate It
11. Extracting Training Data from Diffusion Models
12. Extracting Training Data from Large Language Models
13. HeFUN: Homomorphic Encryption for Unconstrained Secure Neural Network Inference
14. k-Anonymity: A Model for Protecting Privacy
15. l-Diversity: Privacy Beyond k-Anonymity
16. Low-cost high-power membership inference attacks
17. Membership Inference Attacks Against Machine Learning Models
18. Membership Inference Attacks From First Principles
19. Memorization in Deep Learning: A Survey
20. Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures
21. Not What You’ve Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
22. On the Convergence and Calibration of Deep Learning with Differential Privacy
23. OWASP AI Privacy
24. OWASP GenAI Data Security Risks & Mitigations 2026
25. OWASP Top 10 Risk & Mitigations for LLMs and Gen AI Apps
26. Privacy in Deep Learning: A Survey
27. Privacy in Large Language Models: Attacks, Defenses and Future Directions
28. Prompt Injection Attacks in Large Language Models and AI Agent Systems: A Comprehensive Review of Vulnerabilities, Attack Vectors, and Defense Mechanisms
29. RAG & RBAC integration: Protect data and boost AI capabilities
30. Scalable Extraction of Training Data from (Production) Language Models
31. Securing AI Agents: Implementing Role-Based Access Control for Industrial Applications
32. SLENDER: Structured Outputs for SLM-based NER in Low-Resource Englishes
33. SoK: Evaluating Jailbreak Guardrails for Large Language Models
34. SoK: On Gradient Leakage in Federated Learning
35. SPADR: A Context-Aware Pipeline for Privacy Risk Detection in Text Data
36. t-Closeness: Privacy Beyond k-Anonymity and l-Diversity
37. Variational Model Inversion Attacks
38. WildChat: 1M ChatGPT Interaction Logs in the Wild