ai-security

There are 19 repositories under ai-security topic.

h4cker
The-Art-of-Hacking / h4cker
This repository is primarily maintained by Omar Santos (@santosomar) and includes thousands of resources related to ethical hacking, bug bounties, digital forensics and incident response (DFIR), artificial intelligence security, vulnerability research, exploit development, reverse engineering, and more.
ai ai-security artificial-intelligence awesome-list awesome-lists cybersecurity ethical-hacking exploit exploit-development exploits hacker hackers hacking hacking-series penetration-testing training vulnerability vulnerability-assessment vulnerability-identification vulnerability-management
Language:Jupyter Notebook 19024
giskard
Giskard-AI / giskard
🐢 Open-Source Evaluation & Testing for ML & LLM systems
ai-red-team ai-safety ai-security ai-testing ethical-artificial-intelligence evaluation-framework fairness-ai llm llm-eval llm-evaluation llm-security llmops ml-safety ml-testing ml-validation mlops rag-evaluation red-team-tools responsible-ai trustworthy-ai
Language:Python 4079
jiep / offensive-ai-compilation
A curated list of useful resources that cover Offensive AI.
adversarial-machine-learning ai-security artificial-intelligence compilation offensive-ai
Language:HTML 1123
THUYimingLi / backdoor-learning-resources
A list of backdoor learning resources
ai-security backdoor-attacks backdoor-defense backdoor-learning deep-learning machine-learning
1064
normster / llm_rules
RuLES: a benchmark for evaluating rule-following in language models
ai-safety ai-security gpt-4
Language:Python 211
ZhengyuZhao / AI-Security-and-Privacy-Events
A curated list of academic events on AI Security & Privacy
adversarial-examples adversarial-machine-learning ai-privacy ai-security data-poisoning
135
LetterLiGo / SafeGen_CCS2024
[CCS'24] SafeGen: Mitigating Unsafe Content Generation in Text-to-Image Models
ai-safety ai-security generative-ai text-to-image thrustworthy-ai
Language:Python 106
reds-lab / Narcissus
The official implementation of the CCS'23 paper, Narcissus clean-label backdoor attack -- only takes THREE images to poison a face recognition dataset in a clean-label way and achieves a 99.89% attack success rate.
deep-adversarial-attacks adversarial-machine-learning ai-security backdoor-attacks poisoning-attacks
Language:Python 104
RjDuan / AdvDrop
Code for "Adversarial attack by dropping information." (ICCV 2021)
adversarial-attacks adversarial-examples ai-security pytorch
Language:Python 74
jay-johnson / train-ai-with-django-swagger-jwt
Train AI (Keras + Tensorflow) to defend apps with Django REST Framework + Celery + Swagger + JWT - deploys to Kubernetes and OpenShift Container Platform
ai ai-security anti-nex celery celery-tasks deep-neural-networks django-rest-framework drf jwt keras machine-learning machine-learning-security network-analysis network-security openshift rest-api swagger tensorflow
Language:Python 71
Hacking-Notes / VulnScan
Performing website vulnerability scanning using OpenAI technologie
ai-security chatgpt hacking-tool vulnerability-scanners vulnerability-scanning
Language:Python 57
YiZeng623 / I-BAU
Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''
deep-learning adversarial-attacks adversarial-machine-learning ai-security backdoor-attacks backdoor-defense
Language:Jupyter Notebook 50
mitre-atlas / atlas-data
ATLAS tactics, techniques, and case studies data
ai-security machine-learning mitre-atlas mitre-attack security
Language:Python 49
CyberAlbSecOP / Awesome_CyberSec_Bible
Cyber-Security Bible! Theory and Tools, Kali Linux, Penetration Testing, Bug Bounty, CTFs, Malware Analysis, Cryptography, Secure Programming, Web App Security, Cloud Security, Devsecops, Ethical Hacking, Social Engineering, Privacy, Incident Response, Threat Assestment, Personal Security, Ai Security, Android Security, Iot Security, Standards.
ai-security api-security bug-bounty cloud-security cyber-security cybersecurity devsecops ethical-hacking hacking incident-response malware-analysis os-security penetration-testing pentesting privacy security social-engineering threat-intelligence web-application-security
47
CVPR_2019_PNI
elliothe / CVPR_2019_PNI
pytorch implementation of Parametric Noise Injection for adversarial defense
adversarial-defense ai-security
Language:Python 43
Imperio
HKU-TASR / Imperio
[IJCAI 2024] Imperio is an LLM-powered backdoor attack. It allows the adversary to issue language-guided instructions to control the victim model's prediction for arbitrary targets.
ai-security backdoor-attacks llm
Language:Python 41
LetterLiGo / Inaudible-Adversarial-Perturbation-Vrifle
[NDSS'24] Inaudible Adversarial Perturbation: Manipulating the Recognition of User Speech in Real Time
ai-security artificial-intelligence iot-security
Language:Python 34
AnthenaMatrix / Website-Prompt-Injection
Website Prompt Injection is a concept that allows for the injection of prompts into an AI system via a website's. This technique exploits the interaction between users, websites, and AI systems to execute specific prompts that influence AI behavior.
ai aisecurity prompt-engineering prompt-injection cybersecurity security ai-security
Language:HTML 31
wssun / TiSE-LM4Code-Security
This repository provide the studies on the security of language models for code (CodeLMs).
adversarial-attacks adversarial-defense ai-security ai4se backdoor-attacks backdoor-defense code-intelligence language-model lm4se security lm4code
Language:Python 27
AI-Initiative-KAUST / VideoRLCS
Learning to Identify Critical States for Reinforcement Learning from Videos (Accepted to ICCV'23)
ai-security computer-vision deep-learning explainable-ai iccv2023 reinforcement-learning
Language:Python 26
AnthenaMatrix / Prompt-Injection-Testing-Tool
The Prompt Injection Testing Tool is a Python script designed to assess the security of your AI system's prompt handling against a predefined list of user prompts commonly used for injection attacks. This tool utilizes the OpenAI GPT-3.5 model to generate responses to system-user prompt pairs and outputs the results to a CSV file for analysis.
ai ai-cyber-security ai-security openai openai-api prompt prompt-engineering prompt-injection prompt-injection-tool prompt-learning prompting
Language:Python 26
SEC-CAFE / handbook
安全手册，企业安全实践、攻防与安全研究知识库
awesome-security security-wiki security-handbook ai-security llm-security
Language:CSS 25
zhangzp9970 / MIA
Unofficial pytorch implementation of paper: Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures
ai-security deep-learning machine-learning model-inversion-attacks research
Language:Python 25
modzy / sdk-python
Python library for Modzy Machine Learning Operations (MLOps) Platform
mlops python deployment drift-detection explainable-ai kuberenetes machine-learning machine-learning-operations microservices model-deployment model-serving production-machine-learning serving docker ai-security api-client
Language:Python 24
AnthenaMatrix / AI-Prompt-Injection-List
AI/LLM Prompt Injection List is a curated collection of prompts designed for testing AI or Large Language Models (LLMs) for prompt injection vulnerabilities. This list aims to provide a comprehensive set of prompts that can be used to evaluate the behavior of AI or LLM systems when exposed to different types of inputs.
ai aisecurity prompt-engineering prompt-injection ai-security
22
AnthenaMatrix / Image-Prompt-Injection
Image Prompt Injection is a Python script that demonstrates how to embed a secret prompt within an image using steganography techniques. This hidden prompt can be later extracted by an AI system for analysis, enabling covert communication with AI models through images.
ai aisecurity cybersecurity prompt-engineering prompt-injection prompt-injection-tool ai-security
Language:Python 22
jay-johnson / antinex-core
Network exploit detection using highly accurate pre-trained deep neural networks with Celery + Keras + Tensorflow + Redis
celery artificial-intelligence keras tensorflow anti-nex ai-security redis jupyter docker
Language:Jupyter Notebook 21
sachink1729 / Healthcare-AI-Assistant-Medical-Data-Qdrant-Dspy-Groq
Building Private Healthcare AI Assistant for Clinics Using Qdrant Hybrid Cloud, DSPy and Groq - Llama3
ai ai-assistant ai-security dspy-ai groq-api qdrant
Language:Jupyter Notebook 21
wearetyomsmnv / AI-LLM-ML_security_study_map
Do you want to learn AI Security but don't know where to start ? Take a look at this map.
ai-security llm machine-learning-security map ml-security owasp
19
reds-lab / Meta-Sift
The official implementation of USENIX Security'23 paper "Meta-Sift" -- Ten minutes or less to find a 1000-size or larger clean subset on poisoned dataset.
ai-security backdoor-attacks data-poisoning dataset-security
Language:Python 18
modzy / sdk-javascript
The official JavaScript SDK for the Modzy Machine Learning Operations (MLOps) Platform.
javascript ai-security api-client api-rest drift-detection explainable-ai kubernetes machine-learning machine-learning-operations microservices mlops model-serving production-machine-learning
Language:TypeScript 16
moonwatcher-ai / moonwatcher
Evaluation & testing framework for computer vision models
ai-safety ai-security ethical-artificial-intelligence ml-safety ml-testing ml-validation mlops trustworthy-ai computer-vision
Language:Python 16
tsmotlp / AI-Security-Research
A curated collection of the latest academic research papers and developments in AI Security. This repository aims to provide a comprehensive source for researchers and enthusiasts to stay updated on AI Security trends and findings. Contributions welcome!
academic-paper ai-security cyber-security security-research
14
modzy / sdk-java
The official Java library for the Modzy Machine Learning Operations (MLOps) Platform
ai-security api-client docker drift-detection explainable-ai java kubernetes machine-learning machine-learning-operations microservices mlops production-machine-learning
Language:Java 11
Safetorun / PromptDefender
A prompt defence is a multi-layer defence that can be used to protect your applications against prompt injection attacks.
ai ai-security prompt-injection security
Language:Go 11
jay-johnson / antinex-datasets
Datasets for training deep neural networks to defend software applications
ai ai-security anti-nex deep-neural-networks deeplearning django flask keras keras-neural-networks machine-learning machine-learning-security network-security open-data react react-redux rest-api spring tensorflow tensorflow-models vue
Language:Python 8

ai-security

The-Art-of-Hacking / h4cker

Giskard-AI / giskard

jiep / offensive-ai-compilation

THUYimingLi / backdoor-learning-resources

normster / llm_rules

ZhengyuZhao / AI-Security-and-Privacy-Events

LetterLiGo / SafeGen_CCS2024

reds-lab / Narcissus

RjDuan / AdvDrop

jay-johnson / train-ai-with-django-swagger-jwt

Hacking-Notes / VulnScan

YiZeng623 / I-BAU

mitre-atlas / atlas-data

CyberAlbSecOP / Awesome_CyberSec_Bible

elliothe / CVPR_2019_PNI

HKU-TASR / Imperio

LetterLiGo / Inaudible-Adversarial-Perturbation-Vrifle

AnthenaMatrix / Website-Prompt-Injection

wssun / TiSE-LM4Code-Security

AI-Initiative-KAUST / VideoRLCS

AnthenaMatrix / Prompt-Injection-Testing-Tool

SEC-CAFE / handbook

zhangzp9970 / MIA

modzy / sdk-python

AnthenaMatrix / AI-Prompt-Injection-List

AnthenaMatrix / Image-Prompt-Injection

jay-johnson / antinex-core

sachink1729 / Healthcare-AI-Assistant-Medical-Data-Qdrant-Dspy-Groq

wearetyomsmnv / AI-LLM-ML_security_study_map

reds-lab / Meta-Sift

modzy / sdk-javascript

moonwatcher-ai / moonwatcher

tsmotlp / AI-Security-Research

modzy / sdk-java

Safetorun / PromptDefender

jay-johnson / antinex-datasets