22 open-source projects similar to linlt-leon/self-eval, ranked by shared indexed features. Tags may describe platforms or build tools rather than the same primary purpose. Check each project’s use case, license, and deployment requirements before treating it as a replacement.
This repository contains code for the paper Certifying LLM Safety against Adversarial Prompting.
This is the official source code for "SmoothLLM: Defending LLMs Against Jailbreaking Attacks" by Alex Robey, Eric Wong, Hamed Hassani, and George J. Pappas. To learn more about our work, see our blog post.
This is a repository for replicating the experiments from our paper: Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-Tuning .
We have reorganized INDust, aligning evidence with three types of inductive instructions and implementing stricter quality control measures.
2025/09 We have released our code. - 2025/08 Our paper is accepted by EMNLP 2025.
The goal of this project is to create a framework that protects models against both natural language adversarial attacks and its own bias toward mis-alignment. This is done through the usage of a secondary model that judges the prompts to and responses from that primary model. This leaves the…
The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily".
LLM Self Defense: By Self Examination, LLMs know they are being tricked. Mansi Phute, Alec Heibling, Matthew Hull, ShengYun Peng, Sebastian Szyller, Cory Cornelius, Duen Horng Chau. In ICLR 2024 TinyPaper, 2024.
Setting up
RAIN is an innovative inference method that, by integrating self-evaluation and rewind mechanisms, enables frozen large language models to directly produce responses consistent with human preferences without requiring additional alignment data or model fine-tuning, thereby offering an effective…
This is the official implementation for the paper Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing.
This is the official repository for "SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding" (Accepted by ACL 2024).
This is the official code repository for Prefix Guidance: A Steering Wheel for Large Language Models to Defend Against Jailbreak Attacks.
Official Code for ACL 2024 paper "GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis" https://arxiv.org/abs/2402.13494
Defending LLMs against Jailbreaking Attacks via Backtranslation
Overview - Repo Contents - System Requirements - Installation Guide - Demo - Results - License