Cybersecurity - Revision history

BPeat at 21:03, 16 June 2024

2024-06-16T21:03:41Z

BPeat at 01:36, 27 April 2024

2024-04-27T01:36:15Z

BPeat at 15:47, 23 March 2024

2024-03-23T15:47:53Z

BPeat at 03:42, 2 March 2024

2024-03-02T03:42:11Z

BPeat: /* Out-Of-Vocabulary (OOV) */

2023-12-03T17:23:31Z

‎Out-Of-Vocabulary (OOV)

BPeat: /* Out-Of-Vocabulary (OOV) */

2023-12-03T17:17:04Z

‎Out-Of-Vocabulary (OOV)

BPeat: /* Out-Of-Vocabulary (OOV) */

2023-12-03T17:15:05Z

‎Out-Of-Vocabulary (OOV)

BPeat: /* Out-Of-Vocabulary (OOV) */

2023-12-03T17:11:52Z

‎Out-Of-Vocabulary (OOV)

BPeat: /* Data Center Security */

2023-12-03T17:09:15Z

‎Data Center Security

BPeat: /* Data Center Security */

2023-12-03T17:08:55Z

‎Data Center Security

← Older revision		Revision as of 21:03, 16 June 2024
Line 103:		Line 103:

	<youtube>j6S4_cZswWE</youtube>		<youtube>j6S4_cZswWE</youtube>
		+	<youtube>TIj4PBCzcEE</youtube>

	= Risk-based Vulnerability Management (RBVM) =		= Risk-based Vulnerability Management (RBVM) =

@@ Line 29: / Line 29: @@
 * [[Telecommunications#5G Security|5G Security]]
 * [[Time]] ... [[Time#Positioning, Navigation and Timing (PNT)|PNT]] ... [[Time#Global Positioning System (GPS)|GPS]] ... [[Causation vs. Correlation#Retrocausality| Retrocausality]] ... [[Quantum#Delayed Choice Quantum Eraser|Delayed Choice Quantum Eraser]] ... [[Quantum]]
-* [[Development]] ... [[Notebooks]] ... [[Development#AI Pair Programming Tools|AI Pair Programming]] ... [[Codeless Options, Code Generators, Drag n' Drop|Codeless, Generators, Drag n' Drop]] ... [[Algorithm Administration#AIOps/MLOps|AIOps/MLOps]] ... [[Platforms: AI/Machine Learning as a Service (AIaaS/MLaaS)|AIaaS/MLaaS]]
+* [[Development]] ... [[Notebooks]] ... [[Development#AI Pair Programming Tools|AI Pair Programming]] ... [[Codeless Options, Code Generators, Drag n' Drop|Codeless]] ... [[Hugging Face]] ... [[Algorithm Administration#AIOps/MLOps|AIOps/MLOps]] ... [[Platforms: AI/Machine Learning as a Service (AIaaS/MLaaS)|AIaaS/MLaaS]]
 * [[Games - Security]]
 * Useful Models [[...find outliers]]:

← Older revision		Revision as of 15:47, 23 March 2024
Line 101:		Line 101:
	* Security orchestration, automation, and response (SOAR): AI can be used to automate security tasks, such as incident response and remediation.		* Security orchestration, automation, and response (SOAR): AI can be used to automate security tasks, such as incident response and remediation.

		+
		+	<youtube>j6S4_cZswWE</youtube>

	= Risk-based Vulnerability Management (RBVM) =		= Risk-based Vulnerability Management (RBVM) =

@@ Line 244: / Line 244: @@
 <youtube>99hniQYB6VM</youtube>
 <b>Deep Learning For Realtime Malware Detection - Domenic Puzio and Kate Highnam
-</b><br>Domain generation algorithm (DGA) malware makes callouts to unique web addresses to avoid detection by static rules engines. To counter this type of malware, we created an ensemble model that analyzes domains and evaluates if they were generated by a machine and thus potentially malicious. The ensemble consists of two deep learning models – a convolutional neural network and a long short-term memory network, both which were built using Keras and Tensorflow. These deep networks are flexible enough to learn complex patterns and do not require manual feature engineering. Deep learning models are also very difficult for malicious actors to reverse engineer, which makes them an ideal fit for cyber security use cases. The last piece of the ensemble is a natural-language processing model to assess whether the words in the domain make sense together. These three models are able to capture the structure and content of a domain, determining whether or not it comes from DGA malware with very high accuracy. These models have already been used to catch malware that vendor tools did not detect. Our system analyzes enterprise-scale network traffic in real time, renders predictions, and raises alerts for cyber security analysts to evaluate. Domenic Puzio is a Data Engineer with Capital One. He graduated from the University of Virginia with degrees in Mathematics and Computer Science. On his current project he is a core developer of a custom platform for ingesting, processing, and analyzing Capital One’s cyber-security data sources. Built entirely from opensource tools (NiFi, Kafka, Storm, Elasticsearch, Kibana), this framework processes hundreds of millions of events per hour. Currently, his focus is on the creation and productionization of machine learning models that provide enrichment to the data being streamed through the system. He is a contributor to two Apache projects. Kate Highnam has a background in Computer Science and Business, focusing on security, embedded devices, and accounting. At the University of Virginia, her thesis was a published industrial research paper containing an attack scenario and repair algorithm for drones deployed on missions with limited ground control contact. After joining Capital One as a Data Engineer, Kate has developed features within an internal DevOps Pipeline and Data Lake governance system. Currently, she builds machine learning models to assist cybersecurity experts and enhance defenses.
+</b><br>Domain generation algorithm (DGA) malware makes callouts to unique web addresses to avoid detection by static rules engines. To counter this type of malware, we created an ensemble model that analyzes domains and evaluates if they were generated by a machine and thus potentially malicious. The ensemble consists of two deep learning models – a convolutional neural network and a long short-term [[memory]] network, both which were built using Keras and Tensorflow. These deep networks are flexible enough to learn complex patterns and do not require manual feature engineering. Deep learning models are also very difficult for malicious actors to reverse engineer, which makes them an ideal fit for cyber security use cases. The last piece of the ensemble is a natural-language processing model to assess whether the words in the domain make sense together. These three models are able to capture the structure and content of a domain, determining whether or not it comes from DGA malware with very high accuracy. These models have already been used to catch malware that vendor tools did not detect. Our system analyzes enterprise-scale network traffic in real time, renders predictions, and raises alerts for cyber security analysts to evaluate. Domenic Puzio is a Data Engineer with Capital One. He graduated from the University of Virginia with degrees in Mathematics and Computer Science. On his current project he is a core developer of a custom platform for ingesting, processing, and analyzing Capital One’s cyber-security data sources. Built entirely from opensource tools (NiFi, Kafka, Storm, Elasticsearch, Kibana), this framework processes hundreds of millions of events per hour. Currently, his focus is on the creation and productionization of machine learning models that provide enrichment to the data being streamed through the system. He is a contributor to two Apache projects. Kate Highnam has a background in Computer Science and Business, focusing on security, embedded devices, and accounting. At the University of Virginia, her thesis was a published industrial research paper containing an attack scenario and repair algorithm for drones deployed on missions with limited ground control contact. After joining Capital One as a Data Engineer, Kate has developed features within an internal DevOps Pipeline and Data Lake governance system. Currently, she builds machine learning models to assist cybersecurity experts and enhance defenses.
 |}
 |}<!-- B -->

@@ Line 464: / Line 464: @@
 * [[Embedding|Word embedding]]: Representing words as vectors in a high-dimensional space, where similar words are located closer together. This allows the system to infer the meaning of OOV words based on their context and similarity to known words.
-* Morphological analysis: Breaking down words into their constituent morphemes (the smallest meaningful units of language), which can provide clues about the meaning of OOV words.
+* [[Natural Language Processing (NLP)#Stemming (Morphological Similarity)|Morphological analysis]]: Breaking down words into their constituent morphemes (the smallest meaningful units of language), which can provide clues about the meaning of OOV words.
 * [[Unsupervised|Unsupervised learning]]: Using unlabeled data to learn patterns and representations of words, including OOV words, without the need for explicit labeled examples.
 * [[Context|Context-based prediction]]: Utilizing the surrounding words and context to predict the meaning or part of speech of an OOV word.

@@ Line 465: / Line 465: @@
 * Word embedding: Representing words as vectors in a high-dimensional space, where similar words are located closer together. This allows the system to infer the meaning of OOV words based on their context and similarity to known words.
 * Morphological analysis: Breaking down words into their constituent morphemes (the smallest meaningful units of language), which can provide clues about the meaning of OOV words.
-* Unsupervised learning: Using unlabeled data to learn patterns and representations of words, including OOV words, without the need for explicit labeled examples.
+* [[Unsupervised|Unsupervised learning]]: Using unlabeled data to learn patterns and representations of words, including OOV words, without the need for explicit labeled examples.
-* Context-based prediction: Utilizing the surrounding words and context to predict the meaning or part of speech of an OOV word.
+* [[Context|Context-based prediction]]: Utilizing the surrounding words and context to predict the meaning or part of speech of an OOV word.
 The handling of OOV words is an ongoing area of research in NLP, as it is crucial for developing robust and versatile language processing systems that can operate effectively in real-world scenarios.

@@ Line 461: / Line 461: @@
 [https://www.google.com/search?q=ai+eMail+Out+Of+Vocabulary+OOV ...Google search]
-Out-of-vocabulary (OOV) refers to words or phrases that are not found in a predefined vocabulary or lexicon. These words can pose challenges for natural language processing (NLP) tasks, as the model may not be able to recognize or interpret them correctly. OOV words can be encountered in various contexts, such as:
+Out-of-vocabulary (OOV) refers to words or phrases that are not found in a predefined vocabulary or lexicon. These words can pose challenges for natural language processing (NLP) tasks, as the model may not be able to recognize or interpret them correctly. To handle OOV words, NLP systems can employ various techniques, such as:
 * Word embedding: Representing words as vectors in a high-dimensional space, where similar words are located closer together. This allows the system to infer the meaning of OOV words based on their context and similarity to known words.

@@ Line 478: / Line 478: @@
 = Data Center Security =
 [https://www.youtube.com/results?search_query=ai+data+center+security+artificial+intelligence YouTube]
 [https://www.quora.com/search?q=ai%20data%20center%20security%20artificial%20intelligence ... Quora]

@@ Line 480: / Line 480: @@
 [https://www.youtube.com/results?search_query=data+center+security+artificial+intelligence+ai Youtube search...]
 [https://www.google.com/search?q=data+center+security+artificial+intelligence+ai ...Google search]
 {|<!-- T -->