GitHub topics: harmful

Repositories

HKU-TASR/Sanitizer

[EuroS&P 2025] Sanitizer is a server-side method that ensures client-embedded backdoors can only be used for contribution demonstration in federated learning but not be triggered on natural queries in harmful ways.

Language: Python - Size: 78 MB - Last synced at: 3 days ago - Pushed at: 3 days ago - Stars: 3 - Forks: 0

git-disl/awesome_LLM-harmful-fine-tuning-papers

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

Size: 5.64 MB - Last synced at: 8 days ago - Pushed at: 17 days ago - Stars: 157 - Forks: 4

git-disl/Booster

This is the official code for the paper "Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation" (ICLR2025).

Language: Shell - Size: 293 KB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 19 - Forks: 0

git-disl/Virus

This is the official code for the paper "Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation"

Language: Python - Size: 90.3 MB - Last synced at: 2 months ago - Pushed at: 3 months ago - Stars: 41 - Forks: 2

QiBowen2008/WindowsVirusCodes

94种病毒的源代码

Language: Pascal - Size: 1.26 MB - Last synced at: 22 days ago - Pushed at: 9 months ago - Stars: 2 - Forks: 1

git-disl/Vaccine

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

Language: Shell - Size: 730 KB - Last synced at: 5 months ago - Pushed at: 5 months ago - Stars: 19 - Forks: 0

git-disl/Lisa

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

Language: Python - Size: 46.9 KB - Last synced at: 8 months ago - Pushed at: 8 months ago - Stars: 5 - Forks: 0

alessandromonolo/Classification-Of-Days-Exceeding-The-PM-Threshold

The research mainly aims to identify through classification algorithms if one day, based on its climatic features and concentrations of harmful elements in the air, it turns out to be harmful (or not) to the health of citizens in the Milan metropolis. A second prediction model was adopted to predict daily mean PM2.5 values.

Language: Jupyter Notebook - Size: 5.82 MB - Last synced at: 2 months ago - Pushed at: about 3 years ago - Stars: 0 - Forks: 0