Search Results for author:
Found 10 papers, 6 papers with code
Morphence-2.0: Evasion-Resilient Moving Target Defense Powered by Out-of-Distribution Detection
We also show that, when powered by OOD detection, Morphence-2. 0 is able to precisely make an input-based movement of the model's decision function that leads to higher prediction accuracy on both adversarial and benign queries.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
+1
MIAShield: Defending Membership Inference Attacks via Preemptive Exclusion of Members
In membership inference attacks (MIAs), an adversary observes the predictions of a model to determine whether a sample is part of the model's training data.
Rethinking Machine Learning Robustness via its Link with the Out-of-Distribution Problem
Through an OOD to in-distribution mapping intuition, our approach translates OOD inputs to the data distribution used to train and test the model.
DP-UTIL: Comprehensive Utility Analysis of Differential Privacy in Machine Learning
In this paper, we present, DP-UTIL, a holistic utility analysis framework of DP across the ML pipeline with focus on input perturbation, objective perturbation, gradient perturbation, output perturbation, and prediction perturbation.
Morphence: Moving Target Defense Against Adversarial Examples
Attacks often succeed by repeatedly probing a fixed target model with adversarial examples purposely crafted to fool it.
EG-Booster: Explanation-Guided Booster of ML Evasion Attacks
The key insight in EG-Booster is the use of feature-based explanations of model predictions to guide adversarial example crafting by adding consequential perturbations likely to result in model evasion and avoiding non-consequential ones unlikely to contribute to evasion.
Explanation-Guided Diagnosis of Machine Learning Evasion Attacks
Towards systematic assessment of ML evasion attacks, we propose and evaluate a novel suite of model-agnostic metrics for sample-level and dataset-level correlation analysis.
PRICURE: Privacy-Preserving Collaborative Inference in a Multi-Party Setting
This paper presents PRICURE, a system that combines complementary strengths of secure multi-party computation (SMPC) and differential privacy (DP) to enable privacy-preserving collaborative prediction among multiple model owners.
Best-Effort Adversarial Approximation of Black-Box Malware Classifiers
This paper explores best-effort adversarial approximation of a black-box malware classifier in the most challenging setting, where the adversary's knowledge is limited to a prediction label for a given input.
HOLMES: Real-time APT Detection through Correlation of Suspicious Information Flows
In a nutshell, HOLMES aims to produce a detection signal that indicates the presence of a coordinated set of activities that are part of an APT campaign.
Cryptography and Security
