Feature Space Singularity for Out-of-Distribution Detection. (SafeAI 2021)
-
Updated
Feb 15, 2021 - Python
Feature Space Singularity for Out-of-Distribution Detection. (SafeAI 2021)
An educational resource to help anyone learn safe reinforcement learning, inspired by openai/spinningup
An implementation of iterated distillation and amplification
[ICCV2021 Oral] Fooling LiDAR by Attacking GPS Trajectory
A project to add scalable state-of-the-art out-of-distribution detection (open set recognition) support by changing two lines of code! Perform efficient inferences (i.e., do not increase inference time) and detection without classification accuracy drop, hyperparameter tuning, or collecting additional data.
A project to improve out-of-distribution detection (open set recognition) and uncertainty estimation by changing a few lines of code in your project! Perform efficient inferences (i.e., do not increase inference time) without repetitive model training, hyperparameter tuning, or collecting additional data.
Implementation of adaptive constrained RL algorithms. Child repository of @lasgroup/safe-adaptation-gym
a prototype for an AI safety library that allows an agent to maximize its reward by solving a puzzle in order to prevent the worst-case outcomes of perverse instantiation
An interpretability library for pytorch
LAMBDA is a model-based reinforcement learning agent that uses Bayesian world models for safe policy optimization
Hardened AI Assurance reference platform
[Findings of EMNLP 2022] Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks
Aligning AI With Shared Human Values (ICLR 2021)
Stubborn: An Environment for Evaluating Stubbornness between Agents with Aligned Incentives
[Findings of EMNLP 2022] Holistic Sentence Embeddings for Better Out-of-Distribution Detection
LLMs evaluation tool for robustness, consistency, and credibility
This is the official implementation of ContraNet (NDSS2022).
LAWLIA is an open-source computational legal framework designed to revolutionize legal reasoning and analysis. It combines the power of large language models with a structured syntactical grammar to facilitate precise legal assessments, truth values, and verdicts. LAWLIA is the future of computational jurisprudence
Add a description, image, and links to the ai-safety topic page so that developers can more easily learn about it.
To associate your repository with the ai-safety topic, visit your repo's landing page and select "manage topics."