Huan Zhang

Affiliations:
  • Carnegie Mellon University (CMU), Department of Computer Science, Pittsburgh, PA, USA
  • University of California, Los Angeles, CA, USA (former)
  • University of California, Davis, CA, USA (former)
  • IBM T. J. Watson Research Center, Yorktown Heights, NY, USA (former)


According to our database1, Huan Zhang authored at least 83 papers between 2016 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Temporal shuffling for defending deep action recognition models against adversarial attacks.
Neural Networks, January, 2024

F-FOMAML: GNN-Enhanced Meta-Learning for Peak Period Demand Forecasting with Proxy Data.
CoRR, 2024

Neural Network Verification with Branch-and-Bound for General Nonlinearities.
CoRR, 2024

Lyapunov-stable Neural Control for State and Output Feedback: A Novel Formulation for Efficient Synthesis and Verification.
CoRR, 2024

TrustLLM: Trustworthiness in Large Language Models.
CoRR, 2024

Lyapunov-stable Neural Control for State and Output Feedback: A Novel Formulation.
Proceedings of the Forty-first International Conference on Machine Learning, 2024


2023
DiffSmooth: Certifiably Robust Learning via Diffusion Models and Local Smoothing.
Proceedings of the 32nd USENIX Security Symposium, 2023

Provably Bounding Neural Network Preimages.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Towards Robust and Safe Reinforcement Learning with Benign Off-policy Data.
Proceedings of the International Conference on Machine Learning, 2023

On the Robustness of Safe Reinforcement Learning under Observational Perturbations.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Robust Mixture-of-Expert Training for Convolutional Neural Networks.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

2022
FI-ODE: Certified and Robust Forward Invariance in Neural ODEs.
CoRR, 2022

COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks.
CoRR, 2022

General Cutting Planes for Bound-Propagation-Based Neural Network Verification.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagation.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Are AlphaZero-like Agents Robust to Adversarial Perturbations?
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Deep Image Destruction: Vulnerability of Deep Image-to-Image Models against Adversarial Attacks.
Proceedings of the 26th International Conference on Pattern Recognition, 2022

A Branch and Bound Framework for Stronger Adversarial Attacks of ReLU Networks.
Proceedings of the International Conference on Machine Learning, 2022

Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness.
Proceedings of the International Conference on Machine Learning, 2022

COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks.
Proceedings of the Tenth International Conference on Learning Representations, 2022

2021
Improving Robustness of Reinforcement Learning for Power System Control with Adversarial Training.
CoRR, 2021

Deep Image Destruction: A Comprehensive Study on Vulnerability of Deep Image-to-Image Models against Adversarial Attacks.
CoRR, 2021

Fast Certified Robust Training via Better Initialization and Shorter Warmup.
CoRR, 2021

Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Verification.
CoRR, 2021

Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Neural Network Robustness Verification.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Fast Certified Robust Training with Short Warmup.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Robustness between the worst and average case.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Double Perturbation: On the Robustness of Robustness and Counterfactual Bias Evaluation.
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021

Robust Reinforcement Learning on State Observations with Learned Optimal Adversary.
Proceedings of the 9th International Conference on Learning Representations, 2021

Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifiers.
Proceedings of the 9th International Conference on Learning Representations, 2021

2020
Machine Learning with Provable Robustness Guarantees.
PhD thesis, 2020

Spanning attack: reinforce black-box attacks with unlabeled data.
Mach. Learn., 2020

On 𝓁<sub>p</sub>-norm Robustness of Ensemble Stumps and Trees.
CoRR, 2020

The Limit of the Batch Size.
CoRR, 2020

Robust Deep Reinforcement Learning against Adversarial Perturbations on Observations.
CoRR, 2020

Automatic Perturbation Analysis on General Computational Graphs.
CoRR, 2020

An Efficient Adversarial Attack for Tree Ensembles.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

On Lp-norm Robustness of Ensemble Decision Stumps and Trees.
Proceedings of the 37th International Conference on Machine Learning, 2020

Towards Stable and Efficient Training of Verifiably Robust Neural Networks.
Proceedings of the 8th International Conference on Learning Representations, 2020

MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radius.
Proceedings of the 8th International Conference on Learning Representations, 2020

Robustness Verification for Transformers.
Proceedings of the 8th International Conference on Learning Representations, 2020

Adversarially Robust Deep Image Super-Resolution Using Entropy Regularization.
Proceedings of the Computer Vision - ACCV 2020 - 15th Asian Conference on Computer Vision, Kyoto, Japan, November 30, 2020

Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples.
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2019
Enhancing Certifiable Robustness via a Deep Model Ensemble.
CoRR, 2019

Defending Against Adversarial Attacks Using Random Forests.
CoRR, 2019

Towards Stable and Efficient Training of Verifiably Robust Neural Networks.
CoRR, 2019

Second Rethinking of Network Pruning in the Adversarial Setting.
CoRR, 2019

A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Robustness Verification of Tree-based Models.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Robust Decision Trees Against Adversarial Examples.
Proceedings of the 36th International Conference on Machine Learning, 2019

The Limitations of Adversarial Training and the Blind-Spot Attack.
Proceedings of the 7th International Conference on Learning Representations, 2019

Structured Adversarial Attack: Towards General Implementation and Better Interpretability.
Proceedings of the 7th International Conference on Learning Representations, 2019

Query-Efficient Hard-label Black-box Attack: An Optimization-based Approach.
Proceedings of the 7th International Conference on Learning Representations, 2019

Adversarial Robustness vs. Model Compression, or Both?
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

Evaluating Robustness of Deep Image Super-Resolution Against Adversarial Attacks.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

GenAttack: practical black-box attacks with gradient-free optimization.
Proceedings of the Genetic and Evolutionary Computation Conference, 2019

Defending Against Adversarial Attacks Using Random Forest.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2019

RecurJac: An Efficient Recursive Algorithm for Bounding Jacobian Matrix of Neural Networks and Its Applications.
Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, 2019

AutoZOOM: Autoencoder-Based Zeroth Order Optimization Method for Attacking Black-Box Neural Networks.
Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, 2019

2018
Structured Adversarial Attack: Towards General Implementation and Better Interpretability.
CoRR, 2018

Realtime Query Completion via Deep Language Models.
Proceedings of the SIGIR 2018 Workshop On eCommerce co-located with the 41st International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2018), 2018

Efficient Neural Network Robustness Certification with General Activation Functions.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Towards Fast Computation of Certified Robustness for ReLU Networks.
Proceedings of the 35th International Conference on Machine Learning, 2018

Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach.
Proceedings of the 6th International Conference on Learning Representations, 2018

On Extensions of Clever: A Neural Network Robustness Evaluation Algorithm.
Proceedings of the 2018 IEEE Global Conference on Signal and Information Processing, 2018

Is Robustness the Cost of Accuracy? - A Comprehensive Study on the Robustness of 18 Deep Image Classification Models.
Proceedings of the Computer Vision - ECCV 2018, 2018

Towards Robust Neural Networks via Random Self-ensemble.
Proceedings of the Computer Vision - ECCV 2018, 2018

Attacking Visual Language Grounding with Adversarial Examples: A Case Study on Neural Image Captioning.
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, 2018

EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples.
Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018

2017
Show-and-Fool: Crafting Adversarial Examples for Neural Image Captioning.
CoRR, 2017

GPU-acceleration for Large-scale Tree Boosting.
CoRR, 2017

Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Gradient Boosted Decision Trees for High Dimensional Sparse Output.
Proceedings of the 34th International Conference on Machine Learning, 2017

ZOO: Zeroth Order Optimization Based Black-box Attacks to Deep Neural Networks without Training Substitute Models.
Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security, 2017

2016
Sublinear Time Orthogonal Tensor Decomposition.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

A Comprehensive Linear Speedup Analysis for Asynchronous Stochastic Parallel Optimization from Zeroth-Order to First-Order.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

HogWild++: A New Mechanism for Decentralized Asynchronous Stochastic Gradient Descent.
Proceedings of the IEEE 16th International Conference on Data Mining, 2016

Fixing the Convergence Problems in Parallel Asynchronous Dual Coordinate Descent.
Proceedings of the IEEE 16th International Conference on Data Mining, 2016


  Loading...