Difference between revisions of "Offense - Adversarial Threats/Attacks"
| Line 6: | Line 6: | ||
______________________________________________________ | ______________________________________________________ | ||
| + | * [http://blog.openai.com/adversarial-example-research/ Attacking Machine Learning with Adversarial Examples | OpenAI - By Ian Goodfellow, Nicolas Papernot, Sandy Huang, Yan Duan, Pieter Abbeel & Jack Clark] | ||
* [http://arxiv.org/abs/1412.6572 Explaining and Harnessing Adversarial Examples | Ian J. Goodfellow, Jonathon Shlens, Christian Szegedy] | * [http://arxiv.org/abs/1412.6572 Explaining and Harnessing Adversarial Examples | Ian J. Goodfellow, Jonathon Shlens, Christian Szegedy] | ||
| − | + | * [http://www.cleverhans.io/ Cleverhans] - library for benchmarking the vulnerability of machine learning models to adversarial examples blog | |
| − | * [http://www.cleverhans.io/ | ||
* [http://github.com/nababora/advML Adversarial Machine Learning for Anti-Malware Software | nababora @ GitHub] | * [http://github.com/nababora/advML Adversarial Machine Learning for Anti-Malware Software | nababora @ GitHub] | ||
* [http://evademl.org/ EvadeML.org | University of Virginia] | * [http://evademl.org/ EvadeML.org | University of Virginia] | ||
| Line 22: | Line 22: | ||
<youtube>j9FLOinaG94</youtube> | <youtube>j9FLOinaG94</youtube> | ||
<youtube>M2IebCN9Ht4</youtube> | <youtube>M2IebCN9Ht4</youtube> | ||
| − | <youtube> | + | <youtube>gYE9PEaxClo</youtube> |
<youtube>ogP5Ehh_4Rk</youtube> | <youtube>ogP5Ehh_4Rk</youtube> | ||
<youtube>sFhD6ABghf8</youtube> | <youtube>sFhD6ABghf8</youtube> | ||
<youtube>dfgOar_jaG0</youtube> | <youtube>dfgOar_jaG0</youtube> | ||
Revision as of 19:52, 11 June 2018
______________________________________________________
- Attacking Machine Learning with Adversarial Examples | OpenAI - By Ian Goodfellow, Nicolas Papernot, Sandy Huang, Yan Duan, Pieter Abbeel & Jack Clark
- Explaining and Harnessing Adversarial Examples | Ian J. Goodfellow, Jonathon Shlens, Christian Szegedy
- Cleverhans - library for benchmarking the vulnerability of machine learning models to adversarial examples blog
- Adversarial Machine Learning for Anti-Malware Software | nababora @ GitHub
- EvadeML.org | University of Virginia
- AdversariaLib: An Open-source Library for the Security Evaluation of Machine Learning Algorithms Under Attack .pdf
- Pattern Recognition and Applications Lab (PRA Lab)
Adversarial examples are inputs to machine learning models that an attacker has intentionally designed to cause the model to make a mistake; they’re like optical illusions for machines.
