AI News, A Taxonomy and Terminology of Adversarial Machine Learning artificial intelligence
NIST Extends Comment Period for New Adversarial Machine Learning Report
The National Cybersecurity Center for Excellence recently published a draft of its latest cybersecurity draft guide, National Institute of Standards and Technology (NIST) Interagency/Internal Report (NISTIR) 8269, A Taxonomy and Terminology of Adversarial Machine Learning.
Although AI also includes various knowledge-based systems, the data-driven approach of ML introduces additional security challenges in training and testing (inference) phases of system operations.
Taken together, the terminology and taxonomy are intended to inform future standards and best practices for assessing and managing the security of ML components, by establishing a common language and understanding of the rapidly developing AML landscape.
Artificial Intelligence (AI) vs. Machine Learning vs. Deep Learning
You can think of deep learning, machine learning and artificial intelligence as a set of Russian dolls nested within each other, beginning with the smallest and working out.
John McCarthy, widely recognized as one of the godfathers of AI, defined it as “the science and engineering of making intelligent machines.” Here are a few other definitions of artificial intelligence: There are a lot of ways to simulate human intelligence, and some methods are more intelligent than others.
The intelligence that rules engines mimic could be that of an accountant with knowledge of the tax code, who takes information you feed it, runs the information through a set of static rules, and gives your the amount of taxes you owe as a result.
Usually, when a computer program designed by AI researchers actually succeeds at something – like winning at chess – many people say it’s “not really intelligent”, because the algorithm’s internals are well understood.
–Tom Mitchell In 1959, Arthur Samuel, one of the pioneers of machine learning, defined machine learning as a “field of study that gives computers the ability to learn without being explicitly programmed.” That is, machine-learning programs have not been explicitly entered into a computer, like the if-then statements above.
This has three names: an error function, a loss function, or an objective function, because the algorithm has an objective… When someone says they are working with a machine-learning algorithm, you can get to the gist of its value by asking: What’s the objective function?
Deep artificial neural networks are a set of algorithms that have set new records in accuracy for many important problems, such as image recognition, sound recognition, recommender systems, natural language processing etc.
For example, deep learning is part of DeepMind’s well-known AlphaGo algorithm, which beat the former world champion Lee Sedol at Go in early 2016, and the current world champion Ke Jie in early 2017.
So you could apply the same definition to deep learning that Arthur Samuel did to machine learning – a “field of study that gives computers the ability to learn without being explicitly programmed” – while adding that it tends to result in higher accuracy, require more hardware or training time, and perform exceptionally well on machine perception tasks that involved unstructured data such as blobs of pixels or text.
Are we chasing a breakthrough like nuclear fission (possible), or are attempts to wring intelligence from silicon more like trying to turn lead into gold?1 There are four main schools of thought, or churches of belief if you will, that group together how people talk about AI.
In 1404, during the reign of Henry IV, the English parliament passed a law called the “Act against multiplication”, outlawing the creation of gold and silver from other materials, since that was seen as a threat to the throne’s control over the currency.
Multi-objective multi-agent decision making: a utility-based analysis and survey
The majority of multi-agent system implementations aim to optimise agents’ policies with respect to a single objective, despite the fact that many real-world problem domains are inherently multi-objective in nature.
As is standard in multi-objective optimisation, we model the user utility using utility functions that map value or return vectors to scalar values.
This allows us to offer a structured view of the field, to clearly delineate the current state-of-the-art in multi-objective multi-agent decision making approaches and to identify promising directions for future research.