PoCInnovation / Deep-PoC
Deep-PoC is a deepFake detection tool designed to detect deepfakes from videos or images using artificial intelligence.
โ10Updated 2 years ago
Related projects: โ
- Hide some secret ๐ data in a Neural Network - text, malicious software or watermark your NNโ41Updated 2 years ago
- PhD/MSc course on Machine Learning Security (Univ. Cagliari)โ190Updated this week
- A toolkit for detecting and protecting against vulnerabilities in Large Language Models (LLMs).โ116Updated 8 months ago
- Execute anonymization scripts on a table.โ8Updated 2 years ago
- Whispers in the Machine: Confidentiality in LLM-integrated Systemsโ28Updated last week
- BlindBox is a tool to isolate and deploy applications inside Trusted Execution Environments for privacy-by-design appsโ57Updated 10 months ago
- โ30Updated last year
- โ11Updated last year
- The Privacy Adversarial Framework (PAF) is a knowledge base of privacy-focused adversarial tactics and techniques. PAF is heavily inspireโฆโ53Updated last year
- PyTorch-centric library for evaluating and enhancing the robustness of AI technologiesโ51Updated 7 months ago
- this is a repo for the demo on backdoor attacks on StyleGAN and WaveGANโ16Updated 3 years ago
- List of ML file formatsโ34Updated 6 months ago
- ATLAS tactics, techniques, and case studies dataโ46Updated 2 months ago
- source for llmsec.netโ11Updated last month
- Privacy preserving synthetic data generation workflowsโ20Updated 2 years ago
- A re-implementation of the "Extracting Training Data from Large Language Models" paper by Carlini et al., 2020โ30Updated 2 years ago
- โ59Updated last year
- Algorithms for Privacy-Preserving Machine Learning in JAXโ87Updated 3 months ago
- Deep learning model classifying keyboard strokes via phone microphone/Zoom, identifying security threats (Accuracy: 95%)โ33Updated last year
- Risks and targets for assessing LLMs & LLM vulnerabilitiesโ24Updated 3 months ago
- LLM security and privacyโ38Updated 5 months ago
- The spiritual successor to knockknock for PyTorch Lightning, get notified when your training endsโ74Updated this week
- โ42Updated last year
- Privacy backdoorsโ41Updated 4 months ago
- SDNist: Benchmark data and evaluation tools for data synthesizers.โ31Updated 3 months ago
- ๐ Code for the paper: "Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis" (NeurIPS 2021)โ27Updated 2 years ago
- PyTorch implementation of (Hinton) Knowledge Distillation and a base class for simple implementation of other distillation methods.โ25Updated 3 years ago
- A software package for privacy-preserving generation of a synthetic twin to a given sensitive data set.โ46Updated 2 weeks ago
- โ45Updated 11 months ago
- ๐ Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)โ46Updated last year
- Lightweight ML Experiment Logging ๐โ79Updated 3 weeks ago