14 results found Sort:

The-Art-of-Hacking
h4cker The-Art-of-Hacking
3.0k
16.9k
mit
865
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), artif...
ai hacker exploit hackers hacking exploits training ai-security awesome-list awesome-lists cybersecurity vulnerability hacking-series ethical-hacking exploit-development penetration-testing artificial-intelligence vulnerability-assessment vulnerability-management vulnerability-identification
Created 2017-06-19
3,601 commits to master branch, last one 15 days ago
Giskard-AI
giskard Giskard-AI
215
3.4k
apache-2.0
27
🐢 Open-Source Evaluation & Testing for LLMs and ML models
llm mlops llmops llm-eval ai-safety ml-safety ai-testing ml-testing ai-red-team ai-security fairness-ai llm-security ml-validation llm-evaluation rag-evaluation red-team-tools responsible-ai trustworthy-ai model-monitoring ethical-artificial-intelligence
Created 2022-03-06
9,675 commits to main branch, last one a day ago
jiep
offensive-ai-compilation jiep
103
1.0k
cc-by-sa-4.0
25
A curated list of useful resources that cover Offensive AI.
ai-security compilation offensive-ai artificial-intelligence adversarial-machine-learning
Created 2023-01-28
121 commits to main branch, last one 19 days ago
THUYimingLi
backdoor-learning-resources THUYimingLi
164
1.0k
mit
39
A list of backdoor learning resources
ai-security deep-learning backdoor-attacks backdoor-defense machine-learning backdoor-learning
Created 2020-06-13
728 commits to master branch, last one 7 months ago
normster
llm_rules normster
14
197
apache-2.0
3
RuLES: a benchmark for evaluating rule-following in language models
gpt-4 ai-safety ai-security
Created 2023-11-03
22 commits to main branch, last one about a month ago
ZhengyuZhao
AI-Security-and-Privacy-Events ZhengyuZhao
15
117
mit
7
A curated list of academic events on AI Security & Privacy
ai-privacy ai-security data-poisoning adversarial-examples adversarial-machine-learning
Created 2021-10-04
69 commits to main branch, last one 23 days ago
ruoxi-jia-group
Narcissus ruoxi-jia-group
10
93
mit
2
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...
deep- ai-security backdoor-attacks poisoning-attacks adversarial-attacks adversarial-machine-learning
Created 2022-04-08
59 commits to main branch, last one about a year ago
RjDuan
AdvDrop RjDuan
17
70
mit
2
Code for "Adversarial attack by dropping information." (ICCV 2021)
pytorch ai-security adversarial-attacks adversarial-examples
Created 2021-04-12
29 commits to main branch, last one 2 years ago
Hacking-Notes
VulnScan Hacking-Notes
3
51
mit
1
Performing website vulnerability scanning using OpenAI technologie
chatgpt ai-security hacking-tool vulnerability-scanners vulnerability-scanning
Created 2023-02-26
42 commits to main branch, last one about a month ago
YiZeng623
I-BAU YiZeng623
13
46
mit
2
Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''
ai-security deep-learning backdoor-attacks backdoor-defense adversarial-attacks adversarial-machine-learning
Created 2021-10-07
17 commits to main branch, last one about a year ago
HKU-TASR
Imperio HKU-TASR
3
40
mit
4
[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.
llm ai-security backdoor-attacks
Created 2024-01-02
9 commits to main branch, last one about a month ago
mitre-atlas
atlas-data mitre-atlas
8
37
other
3
ATLAS tactics, techniques, and case studies data
security ai-security mitre-atlas mitre-attack machine-learning
Created 2021-12-30
274 commits to main branch, last one about a month ago
AnthenaMatrix
Website-Prompt-Injection AnthenaMatrix
6
32
mit
1
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 exe...
ai security aisecurity ai-security cybersecurity prompt-injection prompt-engineering
Created 2024-03-11
9 commits to main branch, last one 2 months ago
AI-Initiative-KAUST
VideoRLCS AI-Initiative-KAUST
3
25
unknown
1
Learning to Identify Critical States for Reinforcement Learning from Videos (Accepted to ICCV'23)
iccv2023 ai-security deep-learning explainable-ai computer-vision reinforcement-learning
Created 2023-07-18
6 commits to main branch, last one 9 months ago