Huan Zhang

Affiliations

UC DavisUCLA

papers

1,061

total citations

papers (21)

Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations

NEURIPS 2020arXiv

358

citations

COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

ICML 2024arXiv

156

citations

General Cutting Planes for Bound-Propagation-Based Neural Network Verification

NEURIPS 2022arXiv

127

citations

Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds

NEURIPS 2021arXiv

citations

Fast Certified Robust Training with Short Warmup

NEURIPS 2021arXiv

citations

Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagation

NEURIPS 2022arXiv

citations

Robust Mixture-of-Expert Training for Convolutional Neural Networks

ICCV 2023arXiv

citations

Lyapunov-stable Neural Control for State and Output Feedback: A Novel Formulation

ICML 2024arXiv

citations

An Efficient Adversarial Attack for Tree Ensembles

NEURIPS 2020arXiv

citations

Provably Bounding Neural Network Preimages

NEURIPS 2023arXiv

citations

Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks

CVPR 2025arXiv

citations

Stealthy Backdoor Attack in Self-Supervised Learning Vision Encoders for Large Vision Language Models

CVPR 2025arXiv

citations

SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming

ICML 2025arXiv

citations

VIP: Unified Certified Detection and Recovery for Patch Attack with Vision Transformers

ECCV 2022

citations

Robustness between the worst and average case

NEURIPS 2021

citations

Position: TrustLLM: Trustworthiness in Large Language Models

ICML 2024

citations

Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Neural Network Robustness Verification

NEURIPS 2021

citations

Fine-grained Local Sensitivity Analysis of Standard Dot-Product Self-Attention

ICML 2024

citations

Huan Zhang

Affiliations

papers (21)

Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations

COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

General Cutting Planes for Bound-Propagation-Based Neural Network Verification

Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds

Fast Certified Robust Training with Short Warmup

Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagation

Robust Mixture-of-Expert Training for Convolutional Neural Networks

Lyapunov-stable Neural Control for State and Output Feedback: A Novel Formulation

An Efficient Adversarial Attack for Tree Ensembles

Provably Bounding Neural Network Preimages

Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks

Are AlphaZero-like Agents Robust to Adversarial Perturbations?

Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond

Causal Composition Diffusion Model for Closed-loop Traffic Generation

Stealthy Backdoor Attack in Self-Supervised Learning Vision Encoders for Large Vision Language Models

SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming

VIP: Unified Certified Detection and Recovery for Patch Attack with Vision Transformers

Robustness between the worst and average case

Position: TrustLLM: Trustworthiness in Large Language Models

Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Neural Network Robustness Verification

Fine-grained Local Sensitivity Analysis of Standard Dot-Product Self-Attention

papers (21)

Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations

COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

General Cutting Planes for Bound-Propagation-Based Neural Network Verification

Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds

Fast Certified Robust Training with Short Warmup

Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagation

Robust Mixture-of-Expert Training for Convolutional Neural Networks

Lyapunov-stable Neural Control for State and Output Feedback: A Novel Formulation

An Efficient Adversarial Attack for Tree Ensembles

Provably Bounding Neural Network Preimages

Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks

Are AlphaZero-like Agents Robust to Adversarial Perturbations?

Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond

Causal Composition Diffusion Model for Closed-loop Traffic Generation

Stealthy Backdoor Attack in Self-Supervised Learning Vision Encoders for Large Vision Language Models

SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming

VIP: Unified Certified Detection and Recovery for Patch Attack with Vision Transformers

Robustness between the worst and average case

Position: TrustLLM: Trustworthiness in Large Language Models

Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Neural Network Robustness Verification

Fine-grained Local Sensitivity Analysis of Standard Dot-Product Self-Attention