LLM Access Shield: Domain-Specific LLM Framework for Privacy Policy Compliance
Large language models (LLMs) are increasingly applied in fields such as finance, education, and governance due to their ability to generate human-like text and adapt to specialized tasks. However, their widespread adoption raises critical concerns about data privacy and security, including the risk of sensitive data exposure. In this paper, we propose a security framework to enforce policy compliance and mitigate risks in LLM interactions. Our approach introduces three key innovations: (i) LLM-based policy enforcement: a customizable mechanism that enhances domain-specific detection of sensitive data. (ii) Dynamic policy customization: real-time policy adaptation and enforcement during user-LLM interactions to ensure compliance with evolving security requirements. (iii) Sensitive data anonymization: a format-preserving encryption technique that protects sensitive information while maintaining contextual integrity. Experimental results demonstrate that our framework effectively mitigates security risks while preserving the functional accuracy of LLM-driven tasks.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
FLShield: A Validation Based Federated Learning Framework to Defend Against Poisoning Attacks
Federated learning (FL) is revolutionizing how we learn from data. With its growing popularity, it is now being used in many safety-critical domains such as autonomous vehicles and healthcare. Since thousands of particip…
Autonomous VehiclesFederated LearningDataFreeShield: Defending Adversarial Attacks without Training Data
Recent advances in adversarial robustness rely on an abundant set of training data, where using external or additional datasets has become a common setting. However, in real life, the training data is often kept private …
Adversarial RobustnessDataset GenerationUnlearnShield: Shielding Forgotten Privacy against Unlearning Inversion
Machine unlearning is an emerging technique that aims to remove the influence of specific data from trained models, thereby enhancing privacy protection. However, recent research has uncovered critical privacy vulnerabil…
No Privacy Left Outside: On the (In-)Security of TEE-Shielded DNN Partition for On-Device ML
On-device ML introduces new security challenges: DNN models become white-box accessible to device users. Based on white-box information, adversaries can conduct effective model stealing (MS) and membership inference atta…
GPUInference AttackMembership Inference AttackEasy-to-Use Shielding for Reinforcement Learning
Safe exploration is a key challenge in Reinforcement Learning (RL) that aims to prevent agents from making harmful decisions while exploring their environment. Safe exploration is a key challenge in Reinforcement Learnin…
Reinforcement Learning