3 citations · 5 across the 5 of their papers we have counts for
8 papers
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…