In recent times, monocular depth estimation (MDE) has experienced significant advancements in performance, largely attributed to the integration of innovative architectures, i.e., convolutional neural networks (CNNs) and Transformers. Nevertheless, the susceptibility of these models to adversarial attacks has emerged as a noteworthy concern, especially in domains where safety and security are paramount. This concern holds particular weight for MDE due to its critical role in applications like autonomous driving and robotic navigation, where accurate scene understanding is pivotal. To assess the vulnerability of CNN-based depth prediction methods, recent work tries to design adversarial patches against MDE. However, the existing approaches fall short of inducing a comprehensive and substantially disruptive impact on the vision system. Instead, their influence is partial and confined to specific local areas. These methods lead to erroneous depth predictions only within the overlapping region with the input image, without considering the characteristics of the target object, such as its size, shape, and position. In this paper, we introduce a novel adversarial patch named APARATE. This patch possesses the ability to selectively undermine MDE in two distinct ways: by distorting the estimated distances or by creating the illusion of an object disappearing from the perspective of the autonomous system. Notably, APARATE is designed to be sensitive to the shape and scale of the target object, and its influence extends beyond immediate proximity. APARATE, results in a mean depth estimation error surpassing $0.5$, significantly impacting as much as $99\%$ of the targeted region when applied to CNN-based MDE models. Furthermore, it yields a significant error of $0.34$ and exerts substantial influence over $94\%$ of the target region in the context of Transformer-based MDE.

Many metric learning tasks, such as triplet learning, nearest neighbor retrieval, and visualization, are treated primarily as embedding tasks where the ultimate metric is some variant of the Euclidean distance (e.g., cosine or Mahalanobis), and the algorithm must learn to embed points into the pre-chosen space. The study of non-Euclidean geometries is often not explored, which we believe is due to a lack of tools for learning non-Euclidean measures of distance. Recent work has shown that Bregman divergences can be learned from data, opening a promising approach to learning asymmetric distances. We propose a new approach to learning arbitrary Bergman divergences in a differentiable manner via input convex neural networks and show that it overcomes significant limitations of previous works. We also demonstrate that our method more faithfully learns divergences over a set of both new and previously studied tasks, including asymmetric regression, ranking, and clustering. Our tests further extend to known asymmetric, but non-Bregman tasks, where our method still performs competitively despite misspecification, showing the general utility of our approach for asymmetric learning. Learning a task-relevant metric among samples is a common application of machine learning, with use in retrieval, clustering, and ranking. A classic example of retrieval is in visual recognition where, given an object image, the system tries to identify the class based on an existing labeled dataset. To do this, the model can learn a measure of similarity between pairs of images, assigning small distances between images of the same object type. Given the broad successes of deep learning, there has been a recent surge of interest in deep metric learning--using neural networks to automatically learn these similarities (Hoffer & Ailon, 2015; Huang et al., 2016; Zhang et al., 2020). The traditional approach to deep metric learning learns an embedding function over the input space so that a simple distance measure between pairs of embeddings corresponds to task-relevant spatial relations between the inputs. The embedding function f is computed by a neural network, which is learned to encode those spatial relations. First, it is used to define the loss functions, such as triplet or contrastive loss, to dictate how this distance should be used to capture task-relevant properties of the input space. Second, since f is trained to optimize the loss function, the distance influences the learned embedding f.

In this work, we investigate the problem of public data-assisted non-interactive LDP (Local Differential Privacy) learning with a focus on non-parametric classification. Under the posterior drift assumption, we for the first time derive the mini-max optimal convergence rate with LDP constraint. Then, we present a novel approach, the locally private classification tree, which attains the mini-max optimal convergence rate. Furthermore, we design a data-driven pruning procedure that avoids parameter tuning and produces a fast converging estimator. Comprehensive experiments conducted on synthetic and real datasets show the superior performance of our proposed method. Both our theoretical and experimental findings demonstrate the effectiveness of public data compared to private data, which leads to practical suggestions for prioritizing non-private data collection.

We propose data thinning, an approach for splitting an observation into two or more independent parts that sum to the original observation, and that follow the same distribution as the original observation, up to a (known) scaling of a parameter. This very general proposal is applicable to any convolution-closed distribution, a class that includes the Gaussian, Poisson, negative binomial, gamma, and binomial distributions, among others. Data thinning has a number of applications to model selection, evaluation, and inference. For instance, cross-validation via data thinning provides an attractive alternative to the usual approach of cross-validation via sample splitting, especially in settings in which the latter is not applicable. In simulations and in an application to single-cell RNA-sequencing data, we show that data thinning can be used to validate the results of unsupervised learning approaches, such as k-means clustering and principal components analysis, for which traditional sample splitting is unattractive or unavailable.

It is easy to get distracted by US officials pledging to rally support for a "humanitarian pause" and reducing the number of civilian casualties in Israel's bombardment of Gaza. But what matters is the actions of the Biden administration, not empty platitudes. In early November, the US State Department approved a $320m sale of guided bomb kits, reportedly assisting Israel to more precisely hit targets in Gaza. According to The New York Times, "Modern militaries generally add the guidance systems on their bombs with the goal of minimizing civilian casualties, although the damage can still be devastating, especially in urban areas." The United Nations and every major human rights group in the world have routinely condemned Israeli actions in Gaza, along with the Hamas barbarism on October 7, and accused the Israeli army of potentially committing war crimes. Human Rights Watch has rightly called for a suspension of all weapons transfers to Israel and Hamas.

AI expert Marva Bailer tells Fox News Digital how the open availability of artificial intelligence can have negative impacts and talks potential federal legislation to control it. Older Americans reportedly lost $1.1 billion to fraud in 2022, according to the annual Senate Committee on Aging report released this month, and most of the scams utilized AI technology to clone the voices of people they knew and other AI-generated ploys. During a Thursday committee hearing on AI scams, committee chairman Sen. Bob Casey, D-Pa., published the group's annual fraud book highlighting the top scams last year. It found that from January 2020 to June 2021, the FBI found "individuals reportedly lost $13 million to grandparent and person-in-need scams." Sen. Elizabeth Warren, D-Mass, also a member of the committee, said the $1.1 billion figure in total losses is "almost surely an underestimate," since it does not factor in the instances of victims who don't report scams due to embarrassment.

Russia has launched several waves of drone attacks on the Kyiv, Poltava and Cherkasy regions of Ukraine, stepping up its assaults on the Ukrainian capital after several weeks of respite, according to Ukrainian officials. "The enemy's UAVs [unmanned aerial vehicles] were launched in many groups and attacked Kyiv in waves, from different directions, at the same time constantly changing the vectors of movement along the route," Serhiy Popko, the head of Kyiv's military administration, said in a message on Telegram messaging app early on Sunday. "That is why the air raid alerts were announced several times in the capital." Popko said preliminary information indicated that Ukraine's air defence systems downed 10 Iranian-made Shahed kamikaze drones in Kyiv and the city's outskirts. There were no initial reports of "critical damage" or casualties, he said.

Numerous studies have proved their effective strength in detecting Control Area Network (CAN) attacks. In the realm of understanding the human semantic space, transformer-based models have demonstrated remarkable effectiveness. Leveraging pre-trained transformers has become a common strategy in various language-related tasks, enabling these models to grasp human semantics more comprehensively. To delve into the adaptability evaluation on pre-trained models for CAN intrusion detection, we have developed two distinct models: CAN-SecureBERT and CAN-LLAMA2. Notably, our CAN-LLAMA2 model surpasses the state-of-the-art models by achieving an exceptional performance 0.999993 in terms of balanced accuracy, precision detection rate, F1 score, and a remarkably low false alarm rate of 3.10e-6. Impressively, the false alarm rate is 52 times smaller than that of the leading model, MTH-IDS (Multitiered Hybrid Intrusion Detection System). Our study underscores the promise of employing a Large Language Model as the foundational model, while incorporating adapters for other cybersecurity-related tasks and maintaining the model's inherent language-related capabilities.

The advent of Blockchain technology (BT) revolutionised the way remittance transactions are recorded. Banks and remittance organisations have shown a growing interest in exploring blockchain's potential advantages over traditional practices. This paper presents a data-driven predictive decision support approach as an innovative artefact designed for the blockchain-oriented remittance industry. Employing a theory-generating Design Science Research (DSR) approach, we have uncovered the emergence of predictive capabilities driven by transactional big data. The artefact integrates predictive analytics and Machine Learning (ML) to enable real-time remittance monitoring, empowering management decision-makers to address challenges in the uncertain digitised landscape of blockchain-oriented remittance companies. Bridging the gap between theory and practice, this research not only enhances the security of the remittance ecosystem but also lays the foundation for future predictive decision support solutions, extending the potential of predictive analytics to other domains. Additionally, the generated theory from the artifact's implementation enriches the DSR approach and fosters grounded and stakeholder theory development in the information systems domain.

As large language models (LLMs) permeate more and more applications, an assessment of their associated security risks becomes increasingly necessary. The potential for exploitation by malicious actors, ranging from disinformation to data breaches and reputation damage, is substantial. This paper addresses a gap in current research by focusing on the security risks posed by LLMs, which extends beyond the widely covered ethical and societal implications. Our work proposes a taxonomy of security risks along the user-model communication pipeline, explicitly focusing on prompt-based attacks on LLMs. We categorize the attacks by target and attack type within a prompt-based interaction scheme. The taxonomy is reinforced with specific attack examples to showcase the real-world impact of these risks. Through this taxonomy, we aim to inform the development of robust and secure LLM applications, enhancing their safety and trustworthiness.