Adversarial machine learningAdversarial machine learning is the study of the attacks on machine learning algorithms, and of the defenses against such attacks. A survey from May 2020 exposes the fact that practitioners report a dire need for better protecting machine learning systems in industrial applications. To understand, note that most machine learning techniques are mostly designed to work on specific problem sets, under the assumption that the training and test data are generated from the same statistical distribution (IID).
Computer securityComputer security, cyber security, digital security or information technology security (IT security) is the protection of computer systems and networks from attacks by malicious actors that may result in unauthorized information disclosure, theft of, or damage to hardware, software, or data, as well as from the disruption or misdirection of the services they provide. The field is significant due to the expanded reliance on computer systems, the Internet, and wireless network standards such as Bluetooth and Wi-Fi.
MalwareMalware (a portmanteau for malicious software) is any software intentionally designed to cause disruption to a computer, server, client, or computer network, leak private information, gain unauthorized access to information or systems, deprive access to information, or which unknowingly interferes with the user's computer security and privacy. Researchers tend to classify malware into one or more sub-types (i.e. computer viruses, worms, Trojan horses, ransomware, spyware, adware, rogue software, wiper and keyloggers).
Intrusion detection systemAn intrusion detection system (IDS; also intrusion prevention system or IPS) is a device or software application that monitors a network or systems for malicious activity or policy violations. Any intrusion activity or violation is typically reported either to an administrator or collected centrally using a security information and event management (SIEM) system. A SIEM system combines outputs from multiple sources and uses alarm filtering techniques to distinguish malicious activity from false alarms.
Deep learningDeep learning is part of a broader family of machine learning methods, which is based on artificial neural networks with representation learning. The adjective "deep" in deep learning refers to the use of multiple layers in the network. Methods used can be either supervised, semi-supervised or unsupervised.
Types of artificial neural networksThere are many types of artificial neural networks (ANN). Artificial neural networks are computational models inspired by biological neural networks, and are used to approximate functions that are generally unknown. Particularly, they are inspired by the behaviour of neurons and the electrical signals they convey between input (such as from the eyes or nerve endings in the hand), processing, and output from the brain (such as reacting to light, touch, or heat). The way neurons semantically communicate is an area of ongoing research.
Artificial neural networkArtificial neural networks (ANNs, also shortened to neural networks (NNs) or neural nets) are a branch of machine learning models that are built using principles of neuronal organization discovered by connectionism in the biological neural networks constituting animal brains. An ANN is based on a collection of connected units or nodes called artificial neurons, which loosely model the neurons in a biological brain. Each connection, like the synapses in a biological brain, can transmit a signal to other neurons.
Convolutional neural networkConvolutional neural network (CNN) is a regularized type of feed-forward neural network that learns feature engineering by itself via filters (or kernel) optimization. Vanishing gradients and exploding gradients, seen during backpropagation in earlier neural networks, are prevented by using regularized weights over fewer connections. For example, for each neuron in the fully-connected layer 10,000 weights would be required for processing an image sized 100 × 100 pixels.
Feedforward neural networkA feedforward neural network (FNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. Its flow is uni-directional, meaning that the information in the model flows in only one direction—forward—from the input nodes, through the hidden nodes (if any) and to the output nodes, without any cycles or loops, in contrast to recurrent neural networks, which have a bi-directional flow.
Vulnerability (computing)Vulnerabilities are flaws in a computer system that weaken the overall security of the device/system. Vulnerabilities can be weaknesses in either the hardware itself, or the software that runs on the hardware. Vulnerabilities can be exploited by a threat actor, such as an attacker, to cross privilege boundaries (i.e. perform unauthorized actions) within a computer system. To exploit a vulnerability, an attacker must have at least one applicable tool or technique that can connect to a system weakness.
Stable DiffusionStable Diffusion is a deep learning, released in 2022 based on diffusion techniques. It is primarily used to generate detailed images conditioned on text descriptions, though it can also be applied to other tasks such as inpainting, outpainting, and generating image-to-image translations guided by a text prompt. It was developed by researchers from the CompVis Group at Ludwig Maximilian University of Munich and Runway with a compute donation by Stability AI and training data from non-profit organizations.
Recurrent neural networkA recurrent neural network (RNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. In contrast to uni-directional feedforward neural network, it is a bi-directional artificial neural network, meaning that it allows the output from some nodes to affect subsequent input to the same nodes. Their ability to use internal state (memory) to process arbitrary sequences of inputs makes them applicable to tasks such as unsegmented, connected handwriting recognition or speech recognition.
Computer virusA computer virus is a type of malware that, when executed, replicates itself by modifying other computer programs and inserting its own code into those programs. If this replication succeeds, the affected areas are then said to be "infected" with a computer virus, a metaphor derived from biological viruses. Computer viruses generally require a host program. The virus writes its own code into the host program. When the program runs, the written virus program is executed first, causing infection and damage.
Antivirus softwareAntivirus software (abbreviated to AV software), also known as anti-malware, is a computer program used to prevent, detect, and remove malware. Antivirus software was originally developed to detect and remove computer viruses, hence the name. However, with the proliferation of other malware, antivirus software started to protect against other computer threats. Some products also include protection from malicious URLs, spam, and phishing.
Threat (computer)In computer security, a threat is a potential negative action or event facilitated by a vulnerability that results in an unwanted impact to a computer system or application. A threat can be either a negative "intentional" event (i.e. hacking: an individual cracker or a criminal organization) or an "accidental" negative event (e.g. the possibility of a computer malfunctioning, or the possibility of a natural disaster event such as an earthquake, a fire, or a tornado) or otherwise a circumstance, capability, action, or event.
Zero-day (computing)A zero-day (also known as a 0-day) is a computer-software vulnerability previously unknown to those who should be interested in its mitigation, like the vendor of the target software. Until the vulnerability is mitigated, hackers can exploit it to adversely affect programs, data, additional computers or a network. An exploit taking advantage of a zero-day is called a zero-day exploit, or zero-day attack.
Learning classifier systemLearning classifier systems, or LCS, are a paradigm of rule-based machine learning methods that combine a discovery component (e.g. typically a genetic algorithm) with a learning component (performing either supervised learning, reinforcement learning, or unsupervised learning). Learning classifier systems seek to identify a set of context-dependent rules that collectively store and apply knowledge in a piecewise manner in order to make predictions (e.g. behavior modeling, classification, data mining, regression, function approximation, or game strategy).
Common Vulnerabilities and ExposuresThe Common Vulnerabilities and Exposures (CVE) system provides a reference method for publicly known information-security vulnerabilities and exposures. The United States' National Cybersecurity FFRDC, operated by The MITRE Corporation, maintains the system, with funding from the US National Cyber Security Division of the US Department of Homeland Security. The system was officially launched for the public in September 1999. The Security Content Automation Protocol uses CVE, and CVE IDs are listed on Mitre's system as well as in the US National Vulnerability Database.
Mobile securityMobile security, or mobile device security, is the protection of smartphones, tablets, and laptops from threats associated with wireless computing. It has become increasingly important in mobile computing. The security of personal and business information now stored on smartphones is of particular concern. Increasingly, users and businesses use smartphones not only to communicate, but also to plan and organize their work and private life.
Countermeasure (computer)In computer security a countermeasure is an action, device, procedure, or technique that reduces a threat, a vulnerability, or an attack by eliminating or preventing it, by minimizing the harm it can cause, or by discovering and reporting it so that corrective action can be taken. The definition is as IETF RFC 2828 that is the same as CNSS Instruction No. 4009 dated 26 April 2010 by Committee on National Security Systems of United States of America.
