Jinghui Chen

12

Papers

13

Total Citations

Papers (12)

Backdoor Contrastive Learning via Bi-level Trigger Optimization

TruthFlow: Truthful LLM Generation via Representation Flow Correction

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

Graph Adversarial Diffusion Convolution

FADAS: Towards Federated Adaptive Asynchronous Optimization

Do Wider Neural Networks Really Help Adversarial Robustness?

NeurIPS 2021arXiv

One-shot Neural Backdoor Erasing via Adversarial Weight Masking

NeurIPS 2022arXiv

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

NeurIPS 2023arXiv

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

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

NeurIPS 2023arXiv

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

NeurIPS 2023arXiv

A3FL: Adversarially Adaptive Backdoor Attacks to Federated Learning