Picture for Juan Zhai

Juan Zhai

Speculative Coreset Selection for Task-Specific Fine-tuning

Add code
Oct 02, 2024
Viaarxiv icon

Data-centric NLP Backdoor Defense from the Lens of Memorization

Add code
Sep 21, 2024
Viaarxiv icon

Unlocking Adversarial Suffix Optimization Without Affirmative Phrases: Efficient Black-box Jailbreaking via LLM as Optimizer

Add code
Aug 21, 2024
Viaarxiv icon

Efficient DNN-Powered Software with Fair Sparse Models

Add code
Jul 03, 2024
Viaarxiv icon

Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation

Add code
Jun 02, 2024
Viaarxiv icon

Machine Translation Testing via Syntactic Tree Pruning

Add code
Jan 01, 2024
Viaarxiv icon

DREAM: Debugging and Repairing AutoML Pipelines

Add code
Dec 31, 2023
Viaarxiv icon

CILIATE: Towards Fairer Class-based Incremental Learning by Dataset and Training Refinement

Add code
Apr 09, 2023
Viaarxiv icon

UNICORN: A Unified Backdoor Trigger Inversion Framework

Add code
Apr 05, 2023
Viaarxiv icon

Rethinking the Reverse-engineering of Trojan Triggers

Add code
Oct 27, 2022
Viaarxiv icon