8 citations · 24 across the 13 of their papers we have counts for
13 papers
Game of Trojans: Adaptive Adversaries Against Output-based Trojaned-Model Detectors
Dinuka Sahabandu, Xiaojun Xu, Arezoo Rajabi +4
We propose and analyze an adaptive adversary that can retrain a Trojaned DNN and is also aware of SOTA output-based Trojaned model detectors. We show that such an adversary can ens…
Double-Dip: Thwarting Label-Only Membership Inference Attacks with Transfer Learning and Randomization
Arezoo Rajabi, Reeya Pimple, Aiswarya Janardhanan +3
Transfer learning (TL) has been demonstrated to improve DNN model performance when faced with a scarcity of training samples. However, the suitability of TL as a solution to reduce…
MDTD: A Multi Domain Trojan Detector for Deep Neural Networks
Arezoo Rajabi, Surudhi Asokraj, Fengqing Jiang +4
Machine learning models that use deep neural networks (DNNs) are vulnerable to backdoor attacks. An adversary carrying out a backdoor attack embeds a predefined perturbation called…
LDL: A Defense for Label-Based Membership Inference Attacks
Arezoo Rajabi, Dinuka Sahabandu, Luyao Niu +2
The data used to train deep neural network (DNN) models in applications such as healthcare and finance typically contain sensitive information. A DNN model may suffer from overfitt…
Game of Trojans: A Submodular Byzantine Approach
Dinuka Sahabandu, Arezoo Rajabi, Luyao Niu +3
Machine learning models in the wild have been shown to be vulnerable to Trojan attacks during training. Although many detection mechanisms have been proposed, strong adaptive attac…
Trojan Horse Training for Breaking Defenses against Backdoor Attacks in Deep Learning
Arezoo Rajabi, Bhaskar Ramasubramanian, Radha Poovendran
Machine learning (ML) models that use deep neural networks are vulnerable to backdoor attacks. Such attacks involve the insertion of a (hidden) trigger by an adversary. As a conseq…
Privacy-Preserving Reinforcement Learning Beyond Expectation
Arezoo Rajabi, Bhaskar Ramasubramanian, Abdullah Al Maruf +1
Cyber and cyber-physical systems equipped with machine learning algorithms such as autonomous cars share environments with humans. In such a setting, it is important to align syste…
Adversarial Profiles: Detecting Out-Distribution & Adversarial Samples in Pre-trained CNNs
Arezoo Rajabi, Rakesh B. Bobba
Despite high accuracy of Convolutional Neural Networks (CNNs), they are vulnerable to adversarial and out-distribution examples. There are many proposed methods that tend to detect…
Toward Adversarial Robustness by Diversity in an Ensemble of Specialized Deep Neural Networks
Mahdieh Abbasi, Arezoo Rajabi, Christian Gagne +1
We aim at demonstrating the influence of diversity in the ensemble of CNNs on the detection of black-box adversarial instances and hardening the generation of white-box adversarial…
Toward Metrics for Differentiating Out-of-Distribution Sets
Mahdieh Abbasi, Changjian Shui, Arezoo Rajabi +2
Vanilla CNNs, as uncalibrated classifiers, suffer from classifying out-of-distribution (OOD) samples nearly as confidently as in-distribution samples. To tackle this challenge, som…
Controlling Over-generalization and its Effect on Adversarial Examples Generation and Detection
Mahdieh Abbasi, Arezoo Rajabi, Azadeh Sadat Mozafari +2
Convolutional Neural Networks (CNNs) significantly improve the state-of-the-art for many applications, especially in computer vision. However, CNNs still suffer from a tendency to…
Towards Dependable Deep Convolutional Neural Networks (CNNs) with Out-distribution Learning
Mahdieh Abbasi, Arezoo Rajabi, Christian Gagné +1
Detection and rejection of adversarial examples in security sensitive and safety-critical systems using deep CNNs is essential. In this paper, we propose an approach to augment CNN…
DANI: A Fast Diffusion Aware Network Inference Algorithm
Maryam Ramezani, Hamid R. Rabiee, Maryam Tahani +1
The fast growth of social networks and their privacy requirements in recent years, has lead to increasing difficulty in obtaining complete topology of these networks. However, diff…