AttriGuard: A Practical Defense Against Attribute Inference Attacks via Adversarial Machine Learning
arXiv:1805.04810
Abstract
Users in various web and mobile applications are vulnerable to attribute inference attacks, in which an attacker leverages a machine learning classifier to infer a target user's private attributes (e.g., location, sexual orientation, political view) from its public data (e.g., rating scores, page likes). Existing defenses leverage game theory or heuristics based on correlations between the public data and attributes. These defenses are not practical. Specifically, game-theoretic defenses require solving intractable optimization problems, while correlation-based defenses incur large utility loss of users' public data. In this paper, we present AttriGuard, a practical defense against attribute inference attacks. AttriGuard is computationally tractable and has small utility loss. Our AttriGuard works in two phases. Suppose we aim to protect a user's private attribute. In Phase I, for each value of the attribute, we find a minimum noise such that if we add the noise to the user's public data, then the attacker's classifier is very likely to infer the attribute value for the user. We find the minimum noise via adapting existing evasion attacks in adversarial machine learning. In Phase II, we sample one attribute value according to a certain probability distribution and add the corresponding noise found in Phase I to the user's public data. We formulate finding the probability distribution as solving a constrained convex optimization problem. We extensively evaluate AttriGuard and compare it with existing methods using a real-world dataset. Our results show that AttriGuard substantially outperforms existing methods. Our work is the first one that shows evasion attacks can be used as defensive techniques for privacy protection.
27th Usenix Security Symposium, Privacy protection using adversarial examples
References in corpus (3)
Cited by in corpus (24)
- A Survey of Privacy Attacks in Machine Learning
- Poisoning Attacks to Graph-Based Recommender Systems
- BadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvements
- Privacy-Aware Recommendation with Private-Attribute Protection using Adversarial Learning
- Low-Quality Training Data Only? A Robust Framework for Detecting Encrypted Malicious Network Traffic
- Towards a Robust and Trustworthy Machine Learning System Development: An Engineering Perspective
- Synthetic Data: Revisiting the Privacy-Utility Trade-off
- Machine Learning with Membership Privacy using Adversarial Regularization
- Evading classifiers in discrete domains with provable optimality guarantees
- User Consented Federated Recommender System Against Personalized Attribute Inference Attack
- Attacking Graph-based Classification via Manipulating the Graph Structure
- Model Extraction Attacks on Graph Neural Networks: Taxonomy and Realization
- Independent Distribution Regularization for Private Graph Embedding
- Adversarial Security Attacks and Perturbations on Machine Learning and Deep Learning Methods
- Defending against Machine Learning based Inference Attacks via Adversarial Examples: Opportunities and Challenges
- Quantifying and Mitigating Privacy Risks of Contrastive Learning
- Data and Model Dependencies of Membership Inference Attack
- Privacy Inference Attacks and Defenses in Cloud-based Deep Neural Network: A Survey
- Everything About You: A Multimodal Approach towards Friendship Inference in Online Social Networks
- Optimizing Privacy-Preserving Outsourced Convolutional Neural Network Predictions
- 10 Security and Privacy Problems in Large Foundation Models
- Adversarial for Good? How the Adversarial ML Community's Values Impede Socially Beneficial Uses of Attacks
- PrivNet: Safeguarding Private Attributes in Transfer Learning for Recommendation
- Mental Models of Adversarial Machine Learning