Princeton, NJ, USA

Xiangyu Qi

Expert
@Unispac

PHD student @ Princeton ECE.

unispac.github.io

Visual-Adversarial-Examples-Jailbreak-Large-Language-Models. Repository for the Paper (AAAI 2024, Oral) --- Visual Adversarial Examples Jailbreak Large Language Models

282

shallow-vs-deep-alignment. Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep

191

Animation-Avatar-Generation. 基于GAN的动漫头像生成

83

Circumventing-Backdoor-Defenses. Code Repository for the Paper ---Revisiting the Assumption of Latent Separability for Backdoor Defenses (ICLR 2023)

47

Fight-Poison-With-Poison. Code repository for the paper --- [USENIX Security 2023] Towards A Proactive ML Approach for Detecting Backdoor Poison Samples

31

Subnet-Replacement-Attack. Official implementation of (CVPR 2022 Oral) Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks.

27

F-divergence. A very rough reimplementation of < A framework for robustness certification of smoothed classifiers using f-divergence (Dvijotham etc, 2020 ICLR) >.

5

Knowledge-Enhanced-Machine-Learning-Pipeline. Repository for Knowledge Enhanced Machine Learning Pipeline (KEMLP)

1
8
Apply