Pinned Repositories
llm-attacks
Universal and Transferable Attacks on Aligned Language Models
LLMs-Finetuning-Safety
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.
audio-text-multimodel
Fastformer
LLM-Visualization
NRMS
Prefix-Guidance
Recommendation-System-on-MIND
Silent-Guardian
SQL-Injection-Jailbreak