Jinghui Chen

Affiliations

Penn State University

papers

351

total citations

papers (13)

Do Wider Neural Networks Really Help Adversarial Robustness?

NEURIPS 2021arXiv

105

citations

VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models

NEURIPS 2023arXiv

citations

Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks

NEURIPS 2023arXiv

citations

One-shot Neural Backdoor Erasing via Adversarial Weight Masking

NEURIPS 2022arXiv

citations

IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI

NEURIPS 2023arXiv

citations

FADAS: Towards Federated Adaptive Asynchronous Optimization

ICML 2024arXiv

citations

Backdoor Contrastive Learning via Bi-level Trigger Optimization

ICLR 2024arXiv

citations

VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models

AAAI 2024arXiv

citations

UniT: A Unified Look at Certified Robust Training against Text Adversarial Perturbation

NEURIPS 2023

citations

A3FL: Adversarially Adaptive Backdoor Attacks to Federated Learning

NEURIPS 2023

citations

Jinghui Chen

Affiliations

papers (13)

Do Wider Neural Networks Really Help Adversarial Robustness?

VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models

Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks

One-shot Neural Backdoor Erasing via Adversarial Weight Masking

IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI

FADAS: Towards Federated Adaptive Asynchronous Optimization

Backdoor Contrastive Learning via Bi-level Trigger Optimization

VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models

AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion Models

TruthFlow: Truthful LLM Generation via Representation Flow Correction

Graph Adversarial Diffusion Convolution

UniT: A Unified Look at Certified Robust Training against Text Adversarial Perturbation

A3FL: Adversarially Adaptive Backdoor Attacks to Federated Learning

papers (13)

Do Wider Neural Networks Really Help Adversarial Robustness?

VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models

Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks

One-shot Neural Backdoor Erasing via Adversarial Weight Masking

IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI

FADAS: Towards Federated Adaptive Asynchronous Optimization

Backdoor Contrastive Learning via Bi-level Trigger Optimization

VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models

AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion Models

TruthFlow: Truthful LLM Generation via Representation Flow Correction

Graph Adversarial Diffusion Convolution

UniT: A Unified Look at Certified Robust Training against Text Adversarial Perturbation

A3FL: Adversarially Adaptive Backdoor Attacks to Federated Learning