Implementations of SGD on distributed systems create new vulnerabilities, which can be identified and misused by one or more adversarial agents. Recently, it has been shown that well-known Byzantine-resilient gradient aggregation schemes are indeed vulnerable to informed attackers that can tailor the attacks (Fang et al., 2020; Xie et al., 2020b). We introduce MixTailor, a scheme based on randomization of the aggregation strategies that makes it impossible for the attacker to be fully informed. Deterministic schemes can be integrated into MixTailor on the fly without introducing any additional hyperparameters. Randomization decreases the capability of a powerful adversary to tailor its attacks, while the resulting randomized aggregation scheme is still competitive in terms of performance. For both iid and non-iid settings, we establish almost sure convergence guarantees that are both stronger and more general than those available in the literature. Our empirical studies across various datasets, attacks, and settings, validate our hypothesis and show that MixTailor successfully defends when well-known Byzantine-tolerant schemes fail.

Revision is an essential part of the human writing process. It tends to be strategic, adaptive, and, more importantly, iterative in nature. Despite the success of large language models on text revision tasks, they are limited to non-iterative, one-shot revisions. Examining and evaluating the capability of large language models for making continuous revisions and collaborating with human writers is a critical step towards building effective writing assistants. In this work, we present a human-in-the-loop iterative text revision system, Read, Revise, Repeat (R3), which aims at achieving high quality text revisions with minimal human efforts by reading model-generated revisions and user feedbacks, revising documents, and repeating human-machine interactions. In R3, a text revision model provides text editing suggestions for human writers, who can accept or reject the suggested edits. The accepted edits are then incorporated into the model for the next iteration of document revision. Writers can therefore revise documents iteratively by interacting with the system and simply accepting/rejecting its suggested edits until the text revision model stops making further revisions or reaches a predefined maximum number of revisions. Empirical experiments show that R3 can generate revisions with comparable acceptance rate to human writers at early revision depths, and the human-machine interaction can get higher quality revisions with fewer iterations and edits. The collected human-model interaction dataset and system code are available at \url{https://github.com/vipulraheja/IteraTeR}. Our system demonstration is available at \url{https://youtu.be/lK08tIpEoaE}.

We present a multirotor Unmanned Aerial Vehicle control (UAV) and estimation system for supporting replicable research through realistic simulations and real-world experiments. We propose a unique multi-frame localization paradigm for estimating the states of a UAV in various frames of reference using multiple sensors simultaneously. The system enables complex missions in GNSS and GNSS-denied environments, including outdoor-indoor transitions and the execution of redundant estimators for backing up unreliable localization sources. Two feedback control designs are presented: one for precise and aggressive maneuvers, and the other for stable and smooth flight with a noisy state estimate. The proposed control and estimation pipeline are constructed without using the Euler/Tait-Bryan angle representation of orientation in 3D. Instead, we rely on rotation matrices and a novel heading-based convention to represent the one free rotational degree-of-freedom in 3D of a standard multirotor helicopter. We provide an actively maintained and well-documented open-source implementation, including realistic simulation of UAV, sensors, and localization systems. The proposed system is the product of years of applied research on multi-robot systems, aerial swarms, aerial manipulation, motion planning, and remote sensing. All our results have been supported by real-world system deployment that shaped the system into the form presented here. In addition, the system was utilized during the participation of our team from the CTU in Prague in the prestigious MBZIRC 2017 and 2020 robotics competitions, and also in the DARPA SubT challenge. Each time, our team was able to secure top places among the best competitors from all over the world. On each occasion, the challenges has motivated the team to improve the system and to gain a great amount of high-quality experience within tight deadlines.

Counterfactual explanations (CEs) are a powerful means for understanding how decisions made by algorithms can be changed. Researchers have proposed a number of desiderata that CEs should meet to be practically useful, such as requiring minimal effort to enact, or complying with causal models. We consider a further aspect to improve the usability of CEs: robustness to adverse perturbations, which may naturally happen due to unfortunate circumstances. Since CEs typically prescribe a sparse form of intervention (i.e., only a subset of the features should be changed), we study the effect of addressing robustness separately for the features that are recommended to be changed and those that are not. Our definitions are workable in that they can be incorporated as penalty terms in the loss functions that are used for discovering CEs. To experiment with robustness, we create and release code where five data sets (commonly used in the field of fair and explainable machine learning) have been enriched with feature-specific annotations that can be used to sample meaningful perturbations. Our experiments show that CEs are often not robust and, if adverse perturbations take place (even if not worst-case), the intervention they prescribe may require a much larger cost than anticipated, or even become impossible. However, accounting for robustness in the search process, which can be done rather easily, allows discovering robust CEs systematically. Robust CEs make additional intervention to contrast perturbations much less costly than non-robust CEs. We also find that robustness is easier to achieve for the features to change, posing an important point of consideration for the choice of what counterfactual explanation is best for the user. Our code is available at: https://github.com/marcovirgolin/robust-counterfactuals.

The use of meta-rules in logic, i.e., rules whose content includes other rules, has recently gained attention in the setting of non-monotonic reasoning: a first logical formalisation and efficient algorithms to compute the (meta)-extensions of such theories were proposed in Olivieri et al (2021) This work extends such a logical framework by considering the deontic aspect. The resulting logic will not just be able to model policies but also tackle well-known aspects that occur in numerous legal systems. The use of Defeasible Logic (DL) to model meta-rules in the application area we just alluded to has been investigated. Within this line of research, the study mentioned above was not focusing on the general computational properties of meta-rules. This study fills this gap with two major contributions. First, we introduce and formalise two variants of Defeasible Deontic Logic with Meta-Rules to represent (1) defeasible meta-theories with deontic modalities, and (2) two different types of conflicts among rules: Simple Conflict Defeasible Deontic Logic, and Cautious Conflict Defeasible Deontic Logic. Second, we advance efficient algorithms to compute the extensions for both variants.

In the last few months we have seen promising developments in establishing safeguards for AI. This includes a landmark EU regulation proposal on AI that prohibits unacceptable AI uses and imposes mandatory disclosures and evaluations for high-risk systems, an algorithmic transparency standard launched by the UK government, mandatory audits for AI hiring tech in New York City, and a draft AI Risk Assessment Framework developed by NIST at the request of US congress, to name a few. That being said, we are still in the early days of AI regulation. There is a long road ahead to minimize harms that algorithmic systems can cause. In this article series, I explore different topics related to the responsible use of AI and its societal implications.

If you live in a city, it's more likely than not that data is being gathered all around you, the majority of the time. From weather conditions, to traffic patterns and parking, the public is often unaware as to the scale of surveillance that is being used to keep things running smoothly. Now, Monash University has released a report detailing how we can use this data ethically in order to better plan for inclusive and smart future cities. The report, from the Emerging Technologies Research Lab (ETLab) in collaboration with the City of Melbourne, zeroes in on how real-time data can be gathered and used, to improve the city and empower the population. Using technologies like artificial intelligence (AI), Internet of Things (IoT) and 5G, local governments can track things like transportation, sanitation, and climate, to improve urban efficiency and enhance quality of life.

AI thrives on the processing of large volumes of data to be able to deliver focused and targeted solutions. Last year in April, the European Commission (EC) unveiled a legal framework for AI, the Artificial Intelligence Act (AI Act), the first of its kind. The AI Act aims to implement an ecosystem of trust by proposing a legal framework within which people use AI-based solutions while encouraging businesses to develop them. When it comes to technology, Europe has made no secret of its desire to export its values across the world, at least at a principle level. Similar to the General Data Protection Regulation (GDPR), which has become the conventional norm, the AI Act could also become a global precedent, determining to what extent AI may seep into our general day-to-day functioning, or whether it will be limited to automated use by larger entities only.

Industry platforms are foundations that bring people and organizations together for a common purpose, which usually includes making money. They function at the level of a market or ecosystem, rather than only within a specific firm. They often start with products such as operating systems and microprocessors, services such as social media and messaging systems, or marketplaces for e-commerce and financial transactions. They can link thousands, millions, or even billions of users and other market actors. But another type of industry platform has recently received attention from consultants such as The Boston Consulting Group as well as investors, entrepreneurs, and policymakers.

Researchers from Germany's Karlsruhe Institute of Technology (KIT) and pen-maker Stabilo are collaborating on an artificial intelligence (AI)-based pen to teach schoolchildren what is becoming a lost art in an increasingly digital world: handwriting. The joint project--Kaligo-based Intelligent Handwriting Teacher (KIHT)--is funded by the German Federal Ministry of Education and Research. German children are taught to write by redrawing the shape of letters, which requires them to think about writing, explains Tanja Harbaum, a researcher at KIT who is involved with the project. "We want them to be able to write without having to think about writing. That's what we as adults do."