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!
-
Princeton University
- Princeton, NJ
-
02:12
(UTC -05:00) - https://tinghaoxie.com
- @VitusXie
Highlights
- Pro
Pinned Loading
-
SORRY-Bench/sorry-bench
SORRY-Bench/sorry-bench PublicSORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors
Jupyter Notebook 34
-
LLM-Tuning-Safety/LLMs-Finetuning-Safety
LLM-Tuning-Safety/LLMs-Finetuning-Safety PublicWe 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.
-
backdoor-toolbox
backdoor-toolbox PublicA compact toolbox for backdoor attacks and defenses.
-
Unispac/Subnet-Replacement-Attack
Unispac/Subnet-Replacement-Attack PublicOfficial implementation of (CVPR 2022 Oral) Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks.
-
Unispac/Fight-Poison-With-Poison
Unispac/Fight-Poison-With-Poison PublicCode repository for the paper --- [USENIX Security 2023] Towards A Proactive ML Approach for Detecting Backdoor Poison Samples
-
ain-soph/trojanzoo
ain-soph/trojanzoo PublicTrojanZoo provides a universal pytorch platform to conduct security researches (especially backdoor attacks/defenses) of image classification in deep learning.
If the problem persists, check the GitHub status page or contact support.