AI Explainability 360, aka AIX360, provides algorithms that cover the different dimensions of explainability of machine learning models and proxy explainability metrics. The extensible toolkit can help users understand how these models predict labels by various means throughout the AI application lifecycle. Algorithmic research is translated from the lab into actual practice for domains including finance, human capital management, education, and healthcare. The AIX360 toolkit was introduced on August 8, 2019 and can be downloaded from this link. You can access API docs at this link.

The security and robustness of deep neural networks(DNNs) architectures is one of the most important areas of research in the deep learning field. The native complexity of neural networks and its lack of interpretability makes them vulnerable to many forms of attacks. Some of the most sophisticated and scariest forms of attacks on DNNs are generated using other neural networks. Adversarial neural networks(ANNs) are often used to generate numerous attack vectors on DNNs by manipulating aspects such as the input dataset of the training policy. Protecting against adversarial attacks is far from being an easy endeavor as the attackers are always mutating and evolving.

Machine learning models are vulnerable to "adversarial" perturbations (Szegedy et al., 2013; Biggio et al., 2013). They are adversarial in the sense that, after these artificially constructed perturbations are added to on the inputs of the model, human observers do not change their perception, but the predictions ofa model could be manipulated.

Yesterday we announced a new release of the Adversarial Robustness Toolbox, an open-source software library to support researchers and developers in defending neural networks against adversarial attacks. The new release provides a method for defending against poisoning and "backdoor" attacks in machine learning models. We announced the release at Black Hat USA, the world's leading information security event. Machine learning models are often trained on data from potentially untrustworthy sources, including crowd-sourced information, social media data, and user-generated data such as customer satisfaction ratings, purchasing history, or web traffic [1]. Recent work has shown that adversaries can introduce backdoors or "trojans" in machine learning models by poisoning training sets with malicious samples [2].

The advent of artificial intelligence (AI) brought with it a new set of attacks using adversarial AI, and this influx suggests the answer is likely machine. With each innovation in technology comes the reality that attackers who study the security tools will find ways to exploit it. AI can make a phone number look like it's coming from your home area code -- and trick your firewall like a machine learning Trojan horse. How can organizations fight an unknown enemy that's not even human? When cybersecurity company ZeroFOX asked if humans or machines were better hackers back in 2016, they took to Twitter with an automated E2E spear phishing attack.

The Adversarial Robustness Toolbox (ART), an open source software library, supports both researchers and developers in defending deep neural networks against adversarial attacks, making AI systems more secure. Its purpose is to allow rapid crafting and analysis of attack and defense methods for machine learning models. The Adversarial Robustness Toolbox provides an implementation for many state-of-the-art methods for attacking and defending classifiers. It is designed to support researchers and AI developers in creating novel defense techniques and in deploying practical defenses of real-world AI systems. For AI developers, the library provides interfaces that support the composition of comprehensive defense systems using individual methods as building blocks.

In late February 2017, nearly two dozen leading researchers gathered in centuries-old Oxford, England, to warn of the most modern of hazards: malicious use of AI. Among the red flags they raised was an attack called adversarial machine learning. In this scenario, AI systems' neural networks are tricked by intentionally modified external data. An attacker ever so slightly distorts these inputs for the sole purpose of causing AI to misclassify them. An adversarial image of a spoon, for instance, is exactly that -- a spoon -- to human eyes.

IBM today announced the launch of its Adversarial Robustness Toolbox for AI developers. The open-source kit contains everything a machine learning programmer needs to attack their own deep learning neural networks (DNN) to ensure they're able to withstand real-world conditions. The toolbox comes in the form of a code library which includes attack agents, defense utilities, and benchmarking tools that allow developers to integrate baked-in resilience to adversarial attacks. The company says it's the first of its kind. One of the biggest challenges with some of the existing models to defend against adversarial AI is they are very platform specific.