Using techniques in Hashing to match dataframes

Code for "Preference Tuning For Toxicity Mitigation Generalizes Across Languages"

Benchmarking Generalized Out-of-Distribution Detection

[ICML 2023] The official implementation of the paper "TabDDPM: Modelling Tabular Data with Diffusion Models"

Privacy backdoors

A Native-PyTorch Library for LLM Fine-tuning

An Open Robustness Benchmark for Jailbreaking Language Models [arXiv 2024]

End-to-end implementation of ML-based Android malware detectors.

Example: PlatformIO with CubeMX and stm32pio

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

Visualization of Adversarial Examples

Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"

An unrestricted attack based on diffusion models that can achieve both good transferability and imperceptibility.

Implementation of "Beating Backdoor Attack at Its Own Game" (ICCV-23).

A toolkit for polynomial IOPs (PIOPs)

Official repository for CVPR2022 publication, ViM: Out-Of-Distribution with Virtual-logit Matching

write-up

A beautiful, simple, clean, and responsive Jekyll theme for academics

Malware detection using the Drebin dataset

Fast Diffusion Models with Transformers

A new adversarial purification method that uses the forward and reverse processes of diffusion models to remove adversarial perturbations.

PhD Thesis LaTeX Template, according to the rules of Combined Faculty of Natural Sciences and Mathematics, Heidelberg University, Germany

[CVPR23W] "A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion" by Haomin Zhuang, Yihua Zhang and Sijia Liu