Explainable Artificial Intelligence (XAI) aims to improve the transparency of machine learning (ML) pipelines. We systematize the increasingly growing (but fragmented) microcosm of studies that develop and utilize XAI methods for defensive and offensive cybersecurity tasks. We identify 3 cybersecurity stakeholders, i.e., model users, designers, and adversaries, who utilize XAI for 4 distinct objectives within an ML pipeline, namely 1) XAI-enabled user assistance, 2) XAI-enabled model verification, 3) explanation verification & robustness, and 4) offensive use of explanations. Our analysis of the literature indicates that many of the XAI applications are designed with little understanding of how they might be integrated into analyst workflows -- user studies for explanation evaluation are conducted in only 14% of the cases. The security literature sometimes also fails to disentangle the role of the various stakeholders, e.g., by providing explanations to model users and designers while also exposing them to adversaries. Additionally, the role of model designers is particularly minimized in the security literature. To this end, we present an illustrative tutorial for model designers, demonstrating how XAI can help with model verification. We also discuss scenarios where interpretability by design may be a better alternative. The systematization and the tutorial enable us to challenge several assumptions, and present open problems that can help shape the future of XAI research within cybersecurity.

Implicit models separate the definition of a layer from the description of its solution process. While implicit layers allow features such as depth to adapt to new scenarios and inputs automatically, this adaptivity makes its computational expense challenging to predict. In this manuscript, we increase the "implicitness" of the DEQ by redefining the method in terms of an infinite time neural ODE, which paradoxically decreases the training cost over a standard neural ODE by 2-4x. Additionally, we address the question: is there a way to simultaneously achieve the robustness of implicit layers while allowing the reduced computational expense of an explicit layer? To solve this, we develop Skip and Skip Reg. DEQ, an implicit-explicit (IMEX) layer that simultaneously trains an explicit prediction followed by an implicit correction. We show that training this explicit predictor is free and even decreases the training time by 1.11-3.19x. Together, this manuscript shows how bridging the dichotomy of implicit and explicit deep learning can combine the advantages of both techniques.

This paper addresses a new semantic multi-robot planning problem in uncertain and dynamic environments. Particularly, the environment is occupied with non-cooperative, mobile, uncertain labeled targets. These targets are governed by stochastic dynamics while their current and future positions as well as their semantic labels are uncertain. Our goal is to control mobile sensing robots so that they can accomplish collaborative semantic tasks defined over the uncertain current/future positions and labels of these targets. We express these tasks using Linear Temporal Logic (LTL). We propose a sampling-based approach that explores the robot motion space, the mission specification space, as well as the future configurations of the labeled targets to design optimal paths. These paths are revised online to adapt to uncertain perceptual feedback. To the best of our knowledge, this is the first work that addresses semantic mission planning problems in uncertain and dynamic semantic environments. We provide extensive experiments that demonstrate the efficiency of the proposed method

In this work, we study vulnerability of unmanned aerial vehicles (UAVs) to stealthy attacks on perception-based control. To guide our analysis, we consider two specific missions: ($i$) ground vehicle tracking (GVT), and ($ii$) vertical take-off and landing (VTOL) of a quadcopter on a moving ground vehicle. Specifically, we introduce a method to consistently attack both the sensors measurements and camera images over time, in order to cause control performance degradation (e.g., by failing the mission) while remaining stealthy (i.e., undetected by the deployed anomaly detector). Unlike existing attacks that mainly rely on vulnerability of deep neural networks to small input perturbations (e.g., by adding small patches and/or noise to the images), we show that stealthy yet effective attacks can be designed by changing images of the ground vehicle's landing markers as well as suitably falsifying sensing data. We illustrate the effectiveness of our attacks in Gazebo 3D robotics simulator.

Suddenly, the world is abuzz with chatter about chatbots. Artificially intelligent agents, like ChatGPT, have shown themselves to be remarkably adept at conversing in a very human-like fashion. ChatGPT, for instance, recently passed written exams at top business and law schools, among other feats both awe-inspiring and alarming. Researchers at Stanford University's Polarization and Social Change Lab and the Institute for Human-Centered Artificial Intelligence (HAI) wanted to probe the boundaries of AI's political persuasiveness by testing its ability to sway real humans on some of the hottest social issues of the day--an assault weapon ban, the carbon tax, and paid parental leave, among others. Indeed, AI-generated persuasive appeals were as effective as ones written by humans in persuading human audiences on several political issues," said Hui "Max" Bai, a postdoctoral researcher in the Polarization and Social Change Lab and first author on a new paper about the experiment in pre-print.

I will comment on a few topics simplistically to build the foundations of understanding in the articles to come, where I will not go into detail. You can also find some short questions and answers in the previously mentioned article. Sydney is the name of Microsoft's "chatbot" that has been attached to the Bing search engine. Microsoft -- like any big company -- is studying artificial intelligence intensively because whoever dominates AI will dominate the world, AI being a tool more powerful than nuclear weapons by at least 100x (for now). Virtually Artificial Intelligence theoretically has no limits, it can grow in capabilities indefinitely, the only limits being only time and the information it has access.

Despite the repeated and audacious claims by its sometimes CEO, Elon Musk, the prospects of brain-computer interface (BCI) startup Neuralink bringing a product to market remain distant, according to a new report from Reuters. The BCI company was apparently denied authorization by the FDA in 2022 to conduct human trials using the same devices that killed all those pigs -- namely on account of; pig killing. "The agency's major safety concerns involved the device's lithium battery; the potential for the implant's tiny wires to migrate to other areas of the brain; and questions over whether and how the device can be removed without damaging brain tissue," current and former Neuralink employees told Reuters. The FDA's concerns regarding the battery system and its novel transdermal charging capabilities revolve around the the device's chances of failure. According to Reuters, the agency is seeking reassurances that the battery is "very unlikely to fail" because should it do so, the discharge of electrical current or heat energy from a ruptured pack could fry the surrounding tissue.

History has long been a theater of war, the past serving as a proxy in conflicts over the present. Ron DeSantis is warping history by banning books on racism from Florida's schools; people remain divided about the right approach to repatriating Indigenous objects and remains; the Pentagon Papers were an attempt to twist narratives about the Vietnam War. The Nazis seized power in part by manipulating the past--they used propaganda about the burning of the Reichstag, the German parliament building, to justify persecuting political rivals and assuming dictatorial authority. That specific example weighs on Eric Horvitz, Microsoft's chief scientific officer and a leading AI researcher, who tells me that the apparent AI revolution could not only provide a new weapon to propagandists, as social media did earlier this century, but entirely reshape the historiographic terrain, perhaps laying the groundwork for a modern-day Reichstag fire. These are powerful and easy-to-use programs that produce synthetic text, images, video, and audio, all of which can be used by bad actors to fabricate events, people, speeches, and news reports to sow disinformation.

Elon Musk's Nueralink will not be testing its brain implant on humans anytime soon - the US Food and Drug Administration (FDA) has rejected the company's application. The agency outlined dozens of issues the company must address before human testing, a critical milestone for final product approval, Neuralink staffers told Reuters. The concerns include the device's lithium battery; the potential for the implant s tiny wires to migrate to other areas of the brain; and questions over whether and how the device can be removed without damaging brain tissue, the employees said. Musk applied in early 2022, but staffers said the company co-founder has yet to solve all the problems - even though the billionaire revealed human trials would start in six months back in November. Three staffers said they were skeptical the company could quickly resolve the issues.

The future of insurance is here! With the rise of AI, predictive analytics, and chatbots combined with cutting-edge tech like drones, blockchain technology and IoT taking center stage - even the FBI has taken notice. Get ready for a revolution in how we use technology to secure our futures. Then came 2022, when insurers focused on pandemic recovery and meeting customer expectations for digitization and personalization. While adapting to the latest insurance technologies was a challenging experience for many carriers, those who did are selling more benefits faster and smarter than ever before. From underwriting and claims to the customer journey and distribution methods, here are the top insurance technology trends our team believes will be beneficial to carriers in 2023.