Artificial intelligence (A.I.) is becoming a crucial instrument in gathering and analyzing the enemy's intelligence as it plays a bigger part in planning and assisting military operations. The use of autonomous weapons and vehicles is another area in which A.I. is used. Human-machine interfaces for the military, such as machine learning and human-machine teaming, are anticipated to be more impacted by A.I. A.I. is projected to solve the volume, variety, and velocity problems that Big Data presents and lessen the risks associated with issues like veracity and value, allowing for regulated data processing at the level of decisions based on A.I.'s expertise. In many spheres of our society, including policymaking, social life, and the military, the usage of artificial intelligence has increased exponentially. In the latter, artificial intelligence is capable of improving and automating a variety of military duties. However, the same efficiency attained through the employment of algorithms can be easily tricked and hacked, so not everything is beneficial.

Blackbox adversarial attacks can be categorized into transfer- and query-based attacks. Transfer methods do not require any feedback from the victim model, but provide lower success rates compared to query-based methods. Query attacks often require a large number of queries for success. To achieve the best of both approaches, recent efforts have tried to combine them, but still require hundreds of queries to achieve high success rates (especially for targeted attacks). In this paper, we propose a novel method for Blackbox Attacks via Surrogate Ensemble Search (BASES) that can generate highly successful blackbox attacks using an extremely small number of queries. We first define a perturbation machine that generates a perturbed image by minimizing a weighted loss function over a fixed set of surrogate models. To generate an attack for a given victim model, we search over the weights in the loss function using queries generated by the perturbation machine. Since the dimension of the search space is small (same as the number of surrogate models), the search requires a small number of queries. We demonstrate that our proposed method achieves better success rate with at least 30x fewer queries compared to state-of-the-art methods on different image classifiers trained with ImageNet. In particular, our method requires as few as 3 queries per image (on average) to achieve more than a 90% success rate for targeted attacks and 1-2 queries per image for over a 99% success rate for untargeted attacks. Our method is also effective on Google Cloud Vision API and achieved a 91% untargeted attack success rate with 2.9 queries per image. We also show that the perturbations generated by our proposed method are highly transferable and can be adopted for hard-label blackbox attacks. We also show effectiveness of BASES for hiding attacks on object detectors.

Modern state estimation is often formulated as an optimization problem and solved using efficient local search methods. These methods at best guarantee convergence to local minima, but, in some cases, global optimality can also be certified. Although such global optimality certificates have been well established for 3D \textit{pose-graph optimization}, the details have yet to be worked out for the 3D landmark-based SLAM problem, in which estimated states include both robot poses and map landmarks. In this paper, we address this gap by using a graph-theoretic approach to cast the subproblems of landmark-based SLAM into a form that yields a sufficient condition for global optimality. Efficient methods of computing the optimality certificates for these subproblems exist, but first require the construction of a large data matrix. We show that this matrix can be constructed with complexity that remains linear in the number of landmarks and does not exceed the state-of-the-art computational complexity of one local solver iteration. We demonstrate the efficacy of the certificate on simulated and real-world landmark-based SLAM problems. We also integrate our method into the state-of-the-art SE-Sync pipeline to efficiently solve landmark-based SLAM problems to global optimality. Finally, we study the robustness of the global optimality certificate to measurement noise, taking into consideration the effect of the underlying measurement graph.

Cyber deception is emerging as a promising approach to defending networks and systems against attackers and data thieves. However, despite being relatively cheap to deploy, the generation of realistic content at scale is very costly, due to the fact that rich, interactive deceptive technologies are largely hand-crafted. With recent improvements in Machine Learning, we now have the opportunity to bring scale and automation to the creation of realistic and enticing simulated content. In this work, we propose a framework to automate the generation of email and instant messaging-style group communications at scale. Such messaging platforms within organisations contain a lot of valuable information inside private communications and document attachments, making them an enticing target for an adversary. We address two key aspects of simulating this type of system: modelling when and with whom participants communicate, and generating topical, multi-party text to populate simulated conversation threads. We present the LogNormMix-Net Temporal Point Process as an approach to the first of these, building upon the intensity-free modeling approach of Shchur et al. to create a generative model for unicast and multi-cast communications. We demonstrate the use of fine-tuned, pre-trained language models to generate convincing multi-party conversation threads. A live email server is simulated by uniting our LogNormMix-Net TPP (to generate the communication timestamp, sender and recipients) with the language model, which generates the contents of the multi-party email threads. We evaluate the generated content with respect to a number of realism-based properties, that encourage a model to learn to generate content that will engage the attention of an adversary to achieve a deception outcome.

Fairness in multiwinner elections is studied in varying contexts. For instance, diversity of candidates and representation of voters are both separately termed as being fair. A common denominator to ensure fairness across all such contexts is the use of constraints. However, across these contexts, the candidates selected to satisfy the given constraints may systematically lead to unfair outcomes for historically disadvantaged voter populations as the cost of fairness may be borne unequally. Hence, we develop a model to select candidates that satisfy the constraints fairly across voter populations. To do so, the model maps the constrained multiwinner election problem to a problem of fairly allocating indivisible goods. We propose three variants of the model, namely, global, localized, and inter-sectional. Next, we analyze the model's computational complexity, and we present an empirical analysis of the utility traded-off across various settings of our model across the three variants and discuss the impact of Simpson's paradox using synthetic datasets and a dataset of voting at the United Nations. Finally, we discuss the implications of our work for AI and machine learning, especially for studies that use constraints to guarantee fairness.

The availability of compute and data to train larger and larger language models increases the demand for robust methods of benchmarking the true progress of LM training. Recent years witnessed significant progress in standardized benchmarking for English. Benchmarks such as GLUE, SuperGLUE, or KILT have become de facto standard tools to compare large language models. Following the trend to replicate GLUE for other languages, the KLEJ benchmark has been released for Polish. In this paper, we evaluate the progress in benchmarking for low-resourced languages. We note that only a handful of languages have such comprehensive benchmarks. We also note the gap in the number of tasks being evaluated by benchmarks for resource-rich English/Chinese and the rest of the world. In this paper, we introduce LEPISZCZE (the Polish word for glew, the Middle English predecessor of glue), a new, comprehensive benchmark for Polish NLP with a large variety of tasks and high-quality operationalization of the benchmark. We design LEPISZCZE with flexibility in mind. Including new models, datasets, and tasks is as simple as possible while still offering data versioning and model tracking. In the first run of the benchmark, we test 13 experiments (task and dataset pairs) based on the five most recent LMs for Polish. We use five datasets from the Polish benchmark and add eight novel datasets. As the paper's main contribution, apart from LEPISZCZE, we provide insights and experiences learned while creating the benchmark for Polish as the blueprint to design similar benchmarks for other low-resourced languages.

In the U.S., corn is the most produced crop and has been an essential part of the American diet. To meet the demand for supply chain management and regional food security, accurate and timely large-scale corn yield prediction is attracting more attention in precision agriculture. Recently, remote sensing technology and machine learning methods have been widely explored for crop yield prediction. Currently, most county-level yield prediction models use county-level mean variables for prediction, ignoring much detailed information. Moreover, inconsistent spatial resolution between crop area and satellite sensors results in mixed pixels, which may decrease the prediction accuracy. Only a few works have addressed the mixed pixels problem in large-scale crop yield prediction. To address the information loss and mixed pixels problem, we developed a variational autoencoder (VAE) based multiple instance regression (MIR) model for large-scaled corn yield prediction. We use all unlabeled data to train a VAE and the well-trained VAE for anomaly detection. As a preprocess method, anomaly detection can help MIR find a better representation of every bag than traditional MIR methods, thus better performing in large-scale corn yield prediction. Our experiments showed that variational autoencoder based multiple instance regression (VAEMIR) outperformed all baseline methods in large-scale corn yield prediction. Though a suitable meta parameter is required, VAEMIR shows excellent potential in feature learning and extraction for large-scale corn yield prediction.

The Synthetic Control method has pioneered a class of powerful data-driven techniques to estimate the counterfactual reality of a unit from donor units. At its core, the technique involves a linear model fitted on the pre-intervention period that combines donor outcomes to yield the counterfactual. However, linearly combining spatial information at each time instance using time-agnostic weights fails to capture important inter-unit and intra-unit temporal contexts and complex nonlinear dynamics of real data. We instead propose an approach to use local spatiotemporal information before the onset of the intervention as a promising way to estimate the counterfactual sequence. To this end, we suggest a Transformer model that leverages particular positional embeddings, a modified decoder attention mask, and a novel pre-training task to perform spatiotemporal sequence-to-sequence modeling. Our experiments on synthetic data demonstrate the efficacy of our method in the typical small donor pool setting and its robustness against noise. We also generate actionable healthcare insights at the population and patient levels by simulating a state-wide public health policy to evaluate its effectiveness, an in silico trial for asthma medications to support randomized controlled trials, and a medical intervention for patients with Friedreich's ataxia to improve clinical decision-making and promote personalized therapy.

Internet of Things (IoT) networks have become an increasingly attractive target of cyberattacks. Powerful Machine Learning (ML) models have recently been adopted to implement network intrusion detection systems to protect IoT networks. For the successful training of such ML models, selecting the right data features is crucial, maximising the detection accuracy and computational efficiency. This paper comprehensively analyses feature sets' importance and predictive power for detecting network attacks. Three feature selection algorithms: chi-square, information gain and correlation, have been utilised to identify and rank data features. The attributes are fed into two ML classifiers: deep feed-forward and random forest, to measure their attack detection performance. The experimental evaluation considered three datasets: UNSW-NB15, CSE-CIC-IDS2018, and ToN-IoT in their proprietary flow format. In addition, the respective variants in NetFlow format were also considered, i.e., NF-UNSW-NB15, NF-CSE-CIC-IDS2018, and NF-ToN-IoT. The experimental evaluation explored the marginal benefit of adding individual features. Our results show that the accuracy initially increases rapidly with adding features but converges quickly to the maximum. This demonstrates a significant potential to reduce the computational and storage cost of intrusion detection systems while maintaining near-optimal detection accuracy. This has particular relevance in IoT systems, with typically limited computational and storage resources.

Sleep plays a vital role in our physical, cognitive, and psychological well-being. Despite its importance, long-term monitoring of personalized sleep quality (SQ) in real-world contexts is still challenging. Many sleep researches are still developing clinically and far from accessible to the general public. Fortunately, wearables and IoT devices provide the potential to explore the sleep insights from multimodal data, and have been used in some SQ researches. However, most of these studies analyze the sleep related data and present the results in a delayed manner (i.e., today's SQ obtained from last night's data), it is sill difficult for individuals to know how their sleep will be before they go to bed and how they can proactively improve it. To this end, this paper proposes a computational framework to monitor the individual SQ based on both the objective and subjective data from multiple sources, and moves a step further towards providing the personalized feedback to improve the SQ in a data-driven manner. The feedback is implemented by referring the insights from the PMData dataset based on the discovered patterns between life events and different levels of SQ. The deep learning based personal SQ model (PerSQ), using the long-term heterogeneous data and considering the carry-over effect, achieves higher prediction performance compared with baseline models. A case study also shows reasonable results for an individual to monitor and improve the SQ in the future.