clearloveclearlove

Alisa

ALiSa: Acrostic Linguistic Steganography Based on BERT and Gibbs Sampling

BadActs

BEAT

Revisiting-NLP-Backdoor

LLaMA-Factory

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

I-GCG

Improved techniques for optimization-based jailbreaking on large language models (ICLR2025)

AmpleGCG

AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM

learning_research

本人的科研经验

BEEAR

This is the official Gtihub repo for our paper: "BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models".

detection_logits

clearloveclearlove/Alisa

ALiSa: Acrostic Linguistic Steganography Based on BERT and Gibbs Sampling

clearloveclearlove/BadActs

clearloveclearlove/BEAT

clearloveclearlove/Revisiting-NLP-Backdoor