Search Results for author:
Found 14 papers, 4 papers with code
SoK: Unintended Interactions among Machine Learning Defenses and Risks
We survey existing literature on unintended interactions, accommodating them within our framework.
Attesting Distributional Properties of Training Data for Machine Learning
The success of machine learning (ML) has been accompanied by increased concerns about its trustworthiness.
GrOVe: Ownership Verification of Graph Neural Networks using Embeddings
In non-graph settings, fingerprinting models, or the data used to build them, have shown to be a promising approach toward ownership verification.
Inferring Sensitive Attributes from Model Explanations
We focus on the specific privacy risk of attribute inference attack wherein an adversary infers sensitive attributes of an input (e. g., race and sex) given its model explanations.
SHAPr: An Efficient and Versatile Membership Privacy Risk Metric for Machine Learning
Using ten benchmark datasets, we show that SHAPr is indeed effective in estimating susceptibility of training data records to MIAs.
Good Artists Copy, Great Artists Steal: Model Extraction Attacks Against Image Translation Models
We present a framework for conducting such attacks, and show that an adversary can successfully extract functional surrogate models by querying $F_V$ using data from the same domain as the training data for $F_V$.
GECKO: Reconciling Privacy, Accuracy and Efficiency in Embedded Deep Learning
We choose quantization as design choice for highly efficient and private models.
Quantifying (Hyper) Parameter Leakage in Machine Learning
While the attacks proposed in literature are empirical, there is a need for a theoretical framework to measure the information leaked under such extraction attacks.
Fault Tolerance of Neural Networks in Adversarial Settings
Specifically, this work studies the impact of the fault tolerance of the Neural Network on training the model by adding noise to the input (Adversarial Robustness) and noise to the gradients (Differential Privacy).
Towards Enhancing Fault Tolerance in Neural Networks
In the view of difference in functionality, a Neural Network is modelled as two separate networks, i. e, the Feature Extractor with unsupervised learning objective and the Classifier with a supervised learning objective.
Stealing Neural Networks via Timing Side Channels
Deep learning is gaining importance in many applications.
Fuzzy Graph Modelling of Anonymous Networks
Anonymous networks have enabled secure and anonymous communication between the users and service providers while maintaining their anonymity and privacy.
Cryptography and Security Networking and Internet Architecture
