[AAAI 2023] An official PyTorch implementation of paper 'READ: Aggregating Reconstruction Error into Out-of-distribution Detection'
-
Updated
May 30, 2023 - Python
[AAAI 2023] An official PyTorch implementation of paper 'READ: Aggregating Reconstruction Error into Out-of-distribution Detection'
Unofficial implementation of paper "Flexibly Fair Representation Learning by Disentanglement"
Python package to accelerate research on generalized out-of-distribution (OOD) detection.
Scripts to process the reference framework into an object
Initiating a paradigm shift in reporting and helping with making ML advances more considerate of sustainability and trustworthiness.
[AAAI'23 Paper] A machine learning defense for auditors of black box automated decision-making systems.
An open source web platform for assessing Responsible and Trustworthy AI maturity level
Optimization-based deep learning models can give explainability with output guarantees and certificates of trustworthiness.
ObscurePrompt: Jailbreaking Large Language Models via Obscure Input
Neural Additive Models - Visualization Tool in PyTorch/Plotly-Dash
This repository presents a novel approach developed by Prof. Patrick Cheridito and myself for computing conditional expectations with numerical guarantees.
[TIV, 2022] Robust Lane Change Decision Making for Autonomous Vehicles: An Observation Adversarial Reinforcement Learning Approach
Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models. ECCV 2024
Code for the Paper "A Functional Data Perspective and Baseline on Multi-Layer Out-of-Distribution Detection"
Venomancer: Towards Imperceptible and Target-on-Demand Backdoor Attacks in Federated Learning
COMBAT: Alternated Training for Effective Clean-Label Backdoor Attack (AAAI 2024)
Code for paper "FreezeAsGuard: Mitigating Illegal Adaptation of Diffusion Models via Selective Tensor Freezing"
A custom framework designed to analyze and assess Large Language Models (LLMs) for trustworthiness, with a specific focus on detecting excessive agency. This project aims to determine if a language model is assuming more capabilities or authority than it should.
Breaking the Trilemma of Privacy, Utility, Efficiency via Controllable Machine Unlearning
Multi-omics Trustworthy Integration Framework (MoTIF)
Add a description, image, and links to the trustworthy-ai topic page so that developers can more easily learn about it.
To associate your repository with the trustworthy-ai topic, visit your repo's landing page and select "manage topics."