Difference between revisions of "Offense - Adversarial Threats/Attacks"
| Line 21: | Line 21: | ||
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. Myth: An attacker must have access to the model to generate adversarial examples. Fact: Adversarial examples generalize across models trained to perform the same task, even if those models have different architectures and were trained on a different training set. This means an attacker can train their own model, generate adversarial examples against it, and then deploy those adversarial examples against a model they do not have access to. -[http://www.kdnuggets.com/2015/07/deep-learning-adversarial-examples-misconceptions.html Deep Learning Adversarial Examples – Clarifying Misconceptions | Goodfellow et al. ] | 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. Myth: An attacker must have access to the model to generate adversarial examples. Fact: Adversarial examples generalize across models trained to perform the same task, even if those models have different architectures and were trained on a different training set. This means an attacker can train their own model, generate adversarial examples against it, and then deploy those adversarial examples against a model they do not have access to. -[http://www.kdnuggets.com/2015/07/deep-learning-adversarial-examples-misconceptions.html Deep Learning Adversarial Examples – Clarifying Misconceptions | Goodfellow et al. ] | ||
| + | |||
| + | http://www.helpnetsecurity.com/images/posts/endgame-ai-agent.jpg | ||
<youtube>wbRx18VZlYA</youtube> | <youtube>wbRx18VZlYA</youtube> | ||
Revision as of 06:37, 7 July 2018
- Cybersecurity
- Government Services
- Capabilities
- Boolean Satisfiability (SAT) Problem/Satisfiability Modulo Theories (SMT) Solvers
- Defenses Against Adversarial Examples for Deep Neural Networks
______________________________________________________
- Cleverhans - library for benchmarking the vulnerability of machine learning models to adversarial examples blog
- Adversarial Machine Learning for Anti-Malware Software | nababora @ GitHub
- Deep-pwning/Metasploit | Clarence Chio
- EvadeML.org | University of Virginia
- AdversariaLib: An Open-source Library for the Security Evaluation of Machine Learning Algorithms Under Attack
- 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. Myth: An attacker must have access to the model to generate adversarial examples. Fact: Adversarial examples generalize across models trained to perform the same task, even if those models have different architectures and were trained on a different training set. This means an attacker can train their own model, generate adversarial examples against it, and then deploy those adversarial examples against a model they do not have access to. -Deep Learning Adversarial Examples – Clarifying Misconceptions | Goodfellow et al.
