User profiles for Huan Zhang
 | Huan ZhangAssistant Professor at University of Illinois Urbana-Champaign Verified email at illinois.edu Cited by 13296 |
Efficient neural network robustness certification with general activation functions
Finding minimum distortion of adversarial examples and thus certifying robustness in neural
networks classifiers is known to be a challenging problem. Nevertheless, recently it has …
networks classifiers is known to be a challenging problem. Nevertheless, recently it has …
Zoo: Zeroth order optimization based black-box attacks to deep neural networks without training substitute models
Deep neural networks (DNNs) are one of the most prominent technologies of our time, as
they achieve state-of-the-art performance in many machine learning tasks, including but not …
they achieve state-of-the-art performance in many machine learning tasks, including but not …
Ead: elastic-net attacks to deep neural networks via adversarial examples
Recent studies have highlighted the vulnerability of deep neural networks (DNNs) to
adversarial examples—a visually indistinguishable adversarial image can easily be crafted to …
adversarial examples—a visually indistinguishable adversarial image can easily be crafted to …
Towards robust neural networks via random self-ensemble
Recent studies have revealed the vulnerability of deep neural networks-A small adversarial
perturbation that is imperceptible to human can easily make a well-trained deep neural …
perturbation that is imperceptible to human can easily make a well-trained deep neural …
Cost-effective iron-based aqueous redox flow batteries for large-scale energy storage application: A review
H Zhang, C Sun - Journal of Power Sources, 2021 - Elsevier
In order to solve the current energy crisis, it is necessary to develop an economical and
environmentally friendly alternative energy storage system in order to provide potential solutions …
environmentally friendly alternative energy storage system in order to provide potential solutions …
Towards fast computation of certified robustness for relu networks
Verifying the robustness property of a general Rectified Linear Unit (ReLU) network is an NP-complete
problem. Although finding the exact minimum adversarial distortion is hard, giving …
problem. Although finding the exact minimum adversarial distortion is hard, giving …
Beta-crown: Efficient bound propagation with per-neuron split constraints for neural network robustness verification
Bound propagation based incomplete neural network verifiers such as CROWN are very
efficient and can significantly accelerate branch-and-bound (BaB) based complete verification …
efficient and can significantly accelerate branch-and-bound (BaB) based complete verification …
[HTML][HTML] Viral infection and transmission in a large, well-traced outbreak caused by the SARS-CoV-2 Delta variant
…, Z Liu, Q Guo, L Zou, H Zhang, M Zhang… - Nature …, 2022 - nature.com
The SARS-CoV-2 Delta variant has spread rapidly worldwide. To provide data on its virological
profile, we here report the first local transmission of Delta in mainland China. All 167 …
profile, we here report the first local transmission of Delta in mainland China. All 167 …
[HTML][HTML] Notch signaling pathway: architecture, disease, and therapeutics
B Zhou, W Lin, Y Long, Y Yang, H Zhang… - Signal transduction and …, 2022 - nature.com
The NOTCH gene was identified approximately 110 years ago. Classical studies have
revealed that NOTCH signaling is an evolutionarily conserved pathway. NOTCH receptors …
revealed that NOTCH signaling is an evolutionarily conserved pathway. NOTCH receptors …
Can decentralized algorithms outperform centralized algorithms? a case study for decentralized parallel stochastic gradient descent
Most distributed machine learning systems nowadays, including TensorFlow and CNTK, are
built in a centralized fashion. One bottleneck of centralized algorithms lies on high …
built in a centralized fashion. One bottleneck of centralized algorithms lies on high …