Skip to content
View huangtiansheng's full-sized avatar
🌴
On vacation
🌴
On vacation

Organizations

@git-disl @DatabasePractice

Block or report huangtiansheng

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
huangtiansheng/README.md

Hi there 👋 I am Tiansheng Huang

  • I’m currently a third-year PhD candidate from Georgia Tech.
  • I am working on safety alignment for large language models. Particularly, I am interested in red-teaming attacks and defenses for LLMs.

Selected Publications

I try to push myself to publish high quality papers in the periodicity of every three months. Here are the papers I wrote in 2024.

  • [2024/2/2] Vaccine: Perturbation-aware alignment for large language model aginst harmful fine-tuning NeurIPS2024 [paper] [code]
  • [2024/5/28] Lazy safety alignment for large language models against harmful fine-tuning NeurIPS2024 [paper] [code]
  • [2024/8/18] Antidote: Post-fine-tuning safety alignment for large language models against harmful fine-tuning arXiv [paper]
  • [2024/9/3] Booster: Tackling harmful fine-tuning for large language models via attenuating harmful perturbation arXiv [paper] [code] [Openreview]
  • [2024/9/26] Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey arXiv [paper] [repo]

Pinned Loading

  1. git-disl/awesome_LLM-harmful-fine-tuning-papers git-disl/awesome_LLM-harmful-fine-tuning-papers Public

    A survey on harmful fine-tuning attack for large language model

    69 2

  2. git-disl/Vaccine git-disl/Vaccine Public

    This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)

    Shell 16

  3. git-disl/Lisa git-disl/Lisa Public

    This is the official code for the paper "Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning" (NeurIPS2024)

    Python 8

  4. git-disl/Booster git-disl/Booster Public

    This is the official code for the paper "Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation".

    Shell 5