250 citations · 532 across the 72 of their papers we have counts for
6 papers · 1 filter
RamBoAttack: A Robust Query Efficient Deep Neural Network Decision Exploit
Viet Quoc Vo, Ehsan Abbasnejad, Damith C. Ranasinghe
Machine learning models are critically susceptible to evasion attacks from adversarial examples. Generally, adversarial examples, modified inputs deceptively similar to the origina…
TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systems
Bao Gia Doan, Minhui Xue, Shiqing Ma +2
Deep neural networks are vulnerable to attacks from adversarial inputs and, more recently, Trojans to misguide or hijack the model's decision. We expose the existence of an intrigu…
iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients
Miao Zhang, Steven Su, Shirui Pan +3
\textit{Differentiable ARchiTecture Search} (DARTS) has recently become the mainstream of neural architecture search (NAS) due to its efficiency and simplicity. With a gradient-bas…
Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization
Damien Teney, Ehsan Abbasnejad, Simon Lucey +1
Neural networks trained with SGD were recently shown to rely preferentially on linearly-predictive features and can ignore complex, equally-predictive ones. This simplicity bias ca…
All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-training
Islam Nassar, Samitha Herath, Ehsan Abbasnejad +2
Pseudo-labeling is a key component in semi-supervised learning (SSL). It relies on iteratively using the model to generate artificial labels for the unlabeled data to train against…
Learning for Visual Navigation by Imagining the Success
Mahdi Kazemi Moghaddam, Ehsan Abbasnejad, Qi Wu +2
Visual navigation is often cast as a reinforcement learning (RL) problem. Current methods typically result in a suboptimal policy that learns general obstacle avoidance and search…