Search Results for author:
Found 9 papers, 3 papers with code
FairProof : Confidential and Certifiable Fairness for Neural Networks
To this end, we propose \name -- a system that uses Zero-Knowledge Proofs (a cryptographic primitive) to publicly verify the fairness of a model, while maintaining confidentiality.
Identifying and Mitigating the Security Risks of Generative AI
However, GenAI can be used just as well by attackers to generate new attacks and increase the velocity and efficacy of existing attacks.
Can Membership Inferencing be Refuted?
Given a machine learning model, a data point and some auxiliary information, the goal of an MI attack is to determine whether the data point was used to train the model.
Privacy Implications of Shuffling
\ldp deployments are vulnerable to inference attacks as an adversary can link the noisy responses to their identity and subsequently, auxiliary information using the \textit{order} of the data.
A Shuffling Framework for Local Differential Privacy
ldp deployments are vulnerable to inference attacks as an adversary can link the noisy responses to their identity and subsequently, auxiliary information using the order of the data.
Data Privacy in Trigger-Action Systems
Trigger-action platforms (TAPs) allow users to connect independent web-based or IoT services to achieve useful automation.
Cryptography and Security
ShadowNet: A Secure and Efficient On-device Model Inference System for Convolutional Neural Networks
ShadowNet protects the model privacy with Trusted Execution Environment (TEE) while securely outsourcing the heavy linear layers of the model to the untrusted hardware accelerators.
Data-Dependent Differentially Private Parameter Learning for Directed Graphical Models
Our solution optimizes for the utility of inference queries over the DGM and \textit{adds noise that is customized to the properties of the private input dataset and the graph structure of the DGM}.
Concise Explanations of Neural Networks using Adversarial Training
Our first contribution is a theoretical exploration of how these two properties (when using attributions based on Integrated Gradients, or IG) are related to adversarial training, for a class of 1-layer networks (which includes logistic regression models for binary and multi-class classification); for these networks we show that (a) adversarial training using an $\ell_\infty$-bounded adversary produces models with sparse attribution vectors, and (b) natural model-training while encouraging stable explanations (via an extra term in the loss function), is equivalent to adversarial training.
