Search Results for author:
Found 9 papers, 4 papers with code
Dynamic Batch Norm Statistics Update for Natural Robustness
We propose a unified framework consisting of a corruption-detection model and BN statistics update that improves the corruption accuracy of any off-the-shelf trained model.
On the Discredibility of Membership Inference Attacks
We argue that current membership inference attacks can identify memorized subpopulations, but they cannot reliably identify which exact sample in the subpopulation was used during the training.
An Efficient Subpopulation-based Membership Inference Attack
The intuition is that the model response should not be significantly different between the target sample and its subpopulation if it was not a training sample.
User-Level Membership Inference Attack against Metric Embedding Learning
In this paper, we develop a user-level MI attack where the goal is to find if any sample from the target user has been used during training even when no exact training sample is available to the attacker.
Accuracy-Privacy Trade-off in Deep Ensemble: A Membership Inference Perspective
We analyze the impact of various factors in deep ensembles and demonstrate the root cause of the trade-off.
On the Difficulty of Membership Inference Attacks
Recent studies propose membership inference (MI) attacks on deep models, where the goal is to infer if a sample has been used in the training process.
Security of Deep Learning Methodologies: Challenges and Opportunities
Despite the plethora of studies about security vulnerabilities and defenses of deep learning models, security aspects of deep learning methodologies, such as transfer learning, have been rarely studied.
Multitask Learning for Network Traffic Classification
We show that with a large amount of easily obtainable data samples for bandwidth and duration prediction tasks, and only a few data samples for the traffic classification task, one can achieve high accuracy.
A Target-Agnostic Attack on Deep Models: Exploiting Security Vulnerabilities of Transfer Learning
Due to insufficient training data and the high computational cost to train a deep neural network from scratch, transfer learning has been extensively used in many deep-neural-network-based applications.
