Reliable-Trustworthy-AI
Verifier
An implementation of a DeepPoly-based verifier for robustness analysis in deep neural networks
Repository for the Reliable and Trustworthy AI course offered in Fall 2022 at ETH Zürich: implementation of DeepPoly, Robustness Analyzer for Deep Neural Networks
2 stars
1 watching
1 forks
Language: Python
last commit: almost 2 years ago
Linked from 1 awesome list
computer-visiondeep-learningdeep-neural-networksreliable-airobust-machine-learning
Related projects:
Repository | Description | Stars |
---|---|---|
clementsicard/reliable-and-trustworthy-ai-notebooks | Research-focused notebooks on developing robust and secure AI models against adversarial attacks | 1 |
trusted-ai/aix360 | A toolkit for explaining complex AI models and data-driven insights | 1,641 |
vehicle-lang/vehicle | A toolkit for enforcing logical specifications on neural networks | 81 |
tonicai/tonic_validate | A framework for evaluating and monitoring the quality of large language model outputs in Retrieval Augmented Generation applications. | 271 |
vrahli/velisarios | A framework for verifying the correctness of Byzantine fault-tolerant distributed systems | 28 |
eth-sri/diffai | Trains neural networks to be provably robust against adversarial examples using abstract interpretation techniques. | 219 |
guanghelee/neurips19-certificates-of-robustness | Provides a framework for computing tight certificates of adversarial robustness for randomly smoothed classifiers. | 17 |
yyzpiero/rl4redteam | An agent trained to scan for vulnerabilities and exploit them in a simulated network environment | 23 |
valida-xyz/valida | A STARK-based virtual machine designed to improve code reuse, performance and modularity through a custom instruction set, compiler and extensibility features. | 303 |
mit-pdos/perennial | A system for verifying correctness of concurrent and crash-safe systems with recovery procedures | 165 |
andreysharapov/xaience | An online repository providing resources and information on explainable AI, algorithmic fairness, ML security, and related topics | 107 |
borealisai/advertorch | A toolbox for researching and evaluating robustness against attacks on machine learning models | 1,311 |
runtimeverification/avm-semantics | A tool for formally verifying Algorand smart contracts' behavior using property-based testing and symbolic execution | 15 |
hendrycks/robustness | Evaluates and benchmarks the robustness of deep learning models to various corruptions and perturbations in computer vision tasks. | 1,030 |
veridise/picus | Automated tool for verifying uniqueness properties in zero-knowledge proof circuits | 70 |