vtu81

Follow

🥯

Everything

Tinghao Xie vtu81

🥯

Everything

Follow

PhD student in ECE@Princeton, alumni at ZJU.

106 followers · 52 following

Princeton University
Princeton, NJ
03:20 (UTC -04:00)
https://tinghaoxie.com
@VitusXie

Achievements

Achievements

Highlights

Pro

vtu81/README.md

Hi there 👋

Hello, I am Tinghao Xie 谢廷浩, a second year ECE PhD candidate at Princeton advised by Prof. Prateek Mittal. I received my Bachelor degree from Computer Science and Technology at Zhejiang University. Check my website for more information!

Pinned Loading

SORRY-Bench/sorry-bench SORRY-Bench/sorry-bench Public

Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)

Jupyter Notebook 83 7
LLM-Tuning-Safety/LLMs-Finetuning-Safety LLM-Tuning-Safety/LLMs-Finetuning-Safety Public

We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20 via OpenAI’s APIs.

Python 356 38
backdoor-toolbox backdoor-toolbox Public

A compact toolbox for backdoor attacks and defenses.

Python 191 23
Unispac/Subnet-Replacement-Attack Unispac/Subnet-Replacement-Attack Public

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

Jupyter Notebook 27 7
Unispac/Fight-Poison-With-Poison Unispac/Fight-Poison-With-Poison Public

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

Python 30 2
ain-soph/trojanzoo ain-soph/trojanzoo Public

TrojanZoo provides a universal pytorch platform to conduct security researches (especially backdoor attacks/defenses) of image classification in deep learning.

Python 303 66