[NeurIPS 2024 Oral] Aligner: Efficient Alignment by Learning to Correct
-
Updated
Jan 16, 2025 - Python
#
aisafety
Here are 27 public repositories matching this topic...
[CoRL'23] Adversarial Training for Safe End-to-End Driving
-
Updated
Nov 11, 2024 - Python
[ACL 2025 Findings] Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements
-
Updated
Jun 29, 2025 - Python
AI-Generated Video Detection via Perceptual Straightening (NeurIPS2025)
computer-vision cognitive-neuroscience geometric-deep-learning detection-algorithm aisafety aivideo deepfake-detection videogeneration aidetection
-
Updated
Jan 2, 2026 - Python
Can Large Language Models Solve Security Challenges? We test LLMs' ability to interact and break out of shell environments using the OverTheWire wargames environment, showing the models' surprising ability to do action-oriented cyberexploits in shell environments
-
Updated
Aug 21, 2023 - Python
A high-performance string formatter written in Rust. This project detects and blocks LLM prompt injection and jailbreak attacks. It also features a customizable rule-based system and defends against obfuscated prompt attacks.
rust high-performance python3 cybersecurity ai-security aisafety rules-based llm prompt-injection text-security llmsecurity jailbreak-protection
-
Updated
Sep 28, 2025 - Python
[NeurIPS 2024] SACPO (Stepwise Alignment for Constrained Policy Optimization)
-
Updated
Dec 23, 2024 - Python
An official repository for the Capability-Based Scaling Laws for LLM Red-Teaming paper.
-
Updated
Feb 10, 2026 - Python
A benchmark for evaluating hallucinations in large visual language models
ai aisafety visual-language-models hallucination-evaluation hallucination-detection medical-safety medical-visual-language-model
-
Updated
Mar 18, 2025 - Python
Safe Option Critic: Learning Safe Options in the A2OC Architecture
-
Updated
Dec 17, 2018 - Python
Explore techniques to use small models as jailbreaking judges
-
Updated
Sep 18, 2024 - Python
Finetuning of Mistral Nemo 13B on the WildJailbreak dataset to produce a red-teaming model
-
Updated
Sep 18, 2024 - Python
AI Safety Evaluation Library
-
Updated
Dec 9, 2025 - Python
Multi-agent simulation using LLMs. Agents autonomously decide actions for survival, reproduction, and social behavior in a grid world.This project aims to replicate a paper published in 2025 (arXiv:2508.12920).
python simulation alignment agent-based-modeling grok sugarscape aisafety llm ai-testing llm-eval llm-evaluation llm-testing grok-api xai-api
-
Updated
Nov 28, 2025 - Python
Secure AI agent runtime with kernel-hard sandboxing, real-time PII masking, and cryptographic audit trails. Production-ready, open source (GPL-3). Supports OpenAI, Anthropic, xAI, Google, Mistral.
-
Updated
Feb 13, 2026 - Python
Learned Semantic Decoder for Language Models.- Its the little model that sits under a big model's hat to explain what its thinking, just like the little cat's from Cat in the Hat! VOOM > FOOM
ai model-evaluation ai-safety interpretability ai-security aisafety mechanistic-interpretability llm-security model-wellbeing
-
Updated
Jan 11, 2026 - Python
The Reference Implementation for EU AI Act (Article 10). Cryptographic semantic binding to ensure deterministic integrity for High-Risk AI. (NEN/ISO JTC 25 Aligned)
artificial-intelligence ai-agents data-sovereignty data-governance open-standard compliance-as-code aisafety semantic-hashing semantic-layer nen headless-bi ai-act
-
Updated
Feb 14, 2026 - Python
a Python library for peer-to-peer communication over the Yggdrasil network
-
Updated
Sep 19, 2024 - Python
Improve this page
Add a description, image, and links to the aisafety topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the aisafety topic, visit your repo's landing page and select "manage topics."