Robust Object Detection Fusion Against Deception

Repository for the Reliable and Trustworthy AI course offered in Fall 2022 at ETH Zürich: implementation of DeepPoly, Robustness Analyzer for Deep Neural Networks

Breast Cancer Detection - This project tackles the crucial challenge of early breast cancer detection using machine learning techniques. Using Machine learnig algorithms, Support Vector Machine, Randon Forest.

Implementation of the paper: Explain2Attack: Text Adversarial Attacks via Cross-Domain Interpretability (ICPR 2020)

Code of ICLR SRML paper titled "Fair Machine Learning under Limited Demographically Labeled Data"

Investigation of the effects of adversarial attacks and adversarial training on different variants of LSTM and CNN.

👀🛡️ Code for the paper “Carefully Blending Adversarial Training and Purification Improves Adversarial Robustness” by Emanuele Ballarin, Alessio Ansuini and Luca Bortolussi (2024)

MixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed Classifiers

Challenging label noise called BadLabel; Robust label-noise learning called Robust DivideMix

The official implementation code of Paper "PointCVaR: Risk-optimized Outlier Removal for Robust 3D Point Cloud Classification" in AAAI 2024 (Oral)

"RDA: Reciprocal Distribution Alignment for Robust Semi-supervised Learning" by Yue Duan (ECCV 2022)

A collection of algorithms for detecting and handling label noise

A project to train your model from scratch or fine-tune a pretrained model using the losses provided in this library to improve out-of-distribution detection and uncertainty estimation performances. Calibrate your model to produce enhanced uncertainty estimations. Detect out-of-distribution data using the defined score type and threshold.

Semi-Supervised Robust Deep Neural Networks for Multi-Label Classification

[Findings of EMNLP 2022] Holistic Sentence Embeddings for Better Out-of-Distribution Detection

Repository for the paper "An Adversarial Approach for the Robust Classification of Pneumonia from Chest Radiographs"

[ICLR 2023] "Combating Exacerbated Heterogeneity for Robust Models in Federated Learning"

The code of AAAI-21 paper titled "Defending against Backdoors in Federated Learning with Robust Learning Rate".

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.

Robust Reinforcement Learning with the Alternating Training of Learned Adversaries (ATLA) framework