Backward propagation of errors (backpropagation) is a method to minimize objective functions (e.g., loss functions) of deep neural networks by identifying optimal

Immigration agents have used Mobile Fortify to scan the faces of countless people in the US--including many citizens. On Wednesday, the Department of Homeland Security published new details about Mobile Fortify, the face recognition app that federal immigration agents use to identify people in the field, undocumented immigrants and US citizens alike. The details, including the company behind the app, were published as part of DHS's 2025 AI Use Case Inventory, which federal agencies are required to release periodically. The inventory includes two entries for Mobile Fortify--one for Customs and Border Protection (CBP), another for Immigration and Customs Enforcement (ICE)--and says the app is in the "deployment" stage for both. CBP says that Mobile Fortify became "operational" at the beginning of May last year, while ICE got access to it on May 20, 2025.

US Customs and Border Protection is paying General Dynamics to create prototype "quantum sensors," to be used with an AI database to detect fentanyl and other narcotics. United States Customs and Border Protection is paying General Dynamics to create a prototype of "quantum sensors" alongside a "database with artificial intelligence " designed "to detect illicit objects and substances (such as fentanyl) in vehicles, containers, and other devices," according to a contract justification published in a federal register last week. "This database and sensor project will integrate advanced quantum and classical sensing technologies with Artificial Intelligence and ultimately deploy proven concepts and end products anywhere in the CBP environment," the justification document reads. "Under this requirement, CBP will take additional steps to enhance its ability to detect, and thus, significantly reduce the harms of illicit contraband entering the United States of America, thus bolstering national security." The document redacts the name of the company developing the prototype; however, contract details included in the federal register entry reveal that the justification is for a $2.4 million General Dynamics contract that has been public since December 2025.

'We Ain't Seen Nothing Yet'--Trump's Mass Deportations Will Only Grow From Here Militias and far-right extremists believed they would be central to Trump's mass deportation plans. When Donald Trump won a second term as US president a year ago, members of violent militias and far-right extremist groups who had spent years boosting the lie that the 2020 election was rigged were ready to assist the president with delivering on one of his main campaign promises: mass deportations. "I'm willing to help," Richard Mack, a former sheriff who founded the far-right Constitutional Sheriffs and Peace Officers Association, told WIRED at the time, claiming he was in touch with Tom Homan, the man Trump installed as his "border czar." Tim Foley, head of the Arizona Border Recon, which describes itself as a "non-government organization," also told WIRED he was in contact with administration officials. William Teer, then head of the far-right Texas Three Percenters militia, wrote a letter to Trump offering his help.

Backward propagation of errors (backpropagation) is a method to minimize objective functions (e.g., loss functions) of deep neural networks by identifying optimal sets of weights and biases. Imposing constraints on weight precision is often required to alleviate prohibitive workloads on hardware. Despite the remarkable success of backpropagation, the algorithm itself is not capable of considering such constraints unless additional algorithms are applied simultaneously. To address this issue, we propose the constrained backpropagation (CBP) algorithm based on the pseudo-Lagrange multiplier method to obtain the optimal set of weights that satisfy a given set of constraints. The defining characteristic of the proposed CBP algorithm is the utilization of a Lagrangian function (loss function plus constraint function) as its objective function. We considered various types of constraints -- binary, ternary, one-bit shift, and two-bit shift weight constraints. As a post-training method, CBP applied to AlexNet, ResNet-18, ResNet-50, and GoogLeNet on ImageNet, which were pre-trained using the conventional backpropagation. For most cases, the proposed algorithm outperforms the state-of-the-art methods on ImageNet, e.g., 66.6\%, 74.4\%, and 64.0\% top-1 accuracy for ResNet-18, ResNet-50, and GoogLeNet with binary weights, respectively. This highlights CBP as a learning algorithm to address diverse constraints with the minimal performance loss by employing appropriate constraint functions.

Federal records show CBP is moving from testing small drones to making them standard surveillance tools, expanding a network that can follow activity in real time and extend well beyond the border. US Customs and Border Protection is quietly doubling down on a surveillance strategy built around human-portable drones, according to federal contracting records reviewed by WIRED. The shift is pushing border enforcement toward a distributed system that can track activity in real time and, critics warn, may extend well beyond the border. New market research conducted this month shows that, rather than relying on larger, centralized drone platforms, CBP is concentrating on lightweight uncrewed aircraft that can be launched quickly by small teams, remain operational under environmental stress, and relay surveillance data directly to frontline units. The documents emphasize portability, fast setup, and integration with equipment already used by border patrol.

US border patrol is asking companies to submit plans to turn standard 4x4 trucks into AI-powered watchtowers--combining radar, cameras, and autonomous tracking to extend surveillance on demand. A US Customs and Border Protection agent stands guard as hundreds of protesters gather near an ICE facility opposing the detention of undocumented immigrants. The US Department of Homeland Security is seeking to develop a new mobile surveillance platform that fuses artificial intelligence, radar, high-powered cameras, and wireless networking into a single system, according to federal contracting records reviewed by WIRED. The technology would mount on 4x4 vehicles capable of reaching remote areas and transforming into rolling, autonomous observation towers, extending the reach of border surveillance far beyond its current fixed sites. The proposed system surfaced Friday after US Customs and Border Protection quietly published a pre-solicitation notice for what it's calling a Modular Mobile Surveillance System, or M2S2.

Estimating causal effects from observational data is challenging due to selection bias, which leads to imbalanced covariate distributions across treatment groups. Propensity score-based weighting methods are widely used to address this issue by reweighting samples to simulate a randomized controlled trial (RCT). However, the effectiveness of these methods heavily depends on the observed data and the accuracy of the propensity score estimator. For example, inverse propensity weighting (IPW) assigns weights based on the inverse of the propensity score, which can lead to instable weights when propensity scores have high variance-either due to data or model misspecification-ultimately degrading the ability of handling selection bias and treatment effect estimation. To overcome these limitations, we propose Deconfounding Factor Weighting (DFW), a novel propensity score-based approach that leverages the deconfounding factor-to construct stable and effective sample weights. DFW prioritizes less confounded samples while mitigating the influence of highly confounded ones, producing a pseudopopulation that better approximates a RCT. Our approach ensures bounded weights, lower variance, and improved covariate balance.While DFW is formulated for binary treatments, it naturally extends to multi-treatment settings, as the deconfounding factor is computed based on the estimated probability of the treatment actually received by each sample. Through extensive experiments on real-world benchmark and synthetic datasets, we demonstrate that DFW outperforms existing methods, including IPW and CBPS, in both covariate balancing and treatment effect estimation.

Self-supervised learning (SSL) is able to build latent representations that generalize well to unseen data. However, only a few SSL techniques exist for the online CL setting, where data arrives in small minibatches, the model must comply with a fixed computational budget, and task boundaries are absent. We introduce Continual Latent Alignment (CLA), a novel SSL strategy for Online CL that aligns the representations learned by the current model with past representations to mitigate forgetting. We found that our CLA is able to speed up the convergence of the training process in the online scenario, outperforming state-of-the-art approaches under the same computational budget. Surprisingly, we also discovered that using CLA as a pretraining protocol in the early stages of pretraining leads to a better final performance when compared to a full i.i.d. pretraining.