Some major retailers and independent stores have introduced AI body scans, CCTV or facial recognition equipment to identify crimes like shoplifting.

The state-of-the-art deep neural networks (DNNs) are vulnerable against adversarial examples with additive random-like noise perturbations. While such examples are hardly found in the physical world, the image blurring effect caused by object motion, on the other hand, commonly occurs in practice, making the study of which greatly important especially for the widely adopted real-time image processing tasks (e.g., object detection, tracking). In this paper, we initiate the first step to comprehensively investigate the potential hazards of blur effect for DNN, caused by object motion. We propose a novel adversarial attack method that can generate visually natural motion-blurred adversarial examples, named motion-based adversarial blur attack (ABBA). To this end, we first formulate the kernel-prediction-based attack where an input image is convolved with kernels in a pixel-wise way, and the misclassification capability is achieved by tuning the kernel weights.

Graph embedding methods represent nodes in a continuous vector space, preserving different types of relational information from the graph. There are many hyper-parameters to these methods (e.g. the length of a random walk) which have to be manually tuned for every graph. In this paper, we replace previously fixed hyper-parameters with trainable ones that we automatically learn via backpropagation. In particular, we propose a novel attention model on the power series of the transition matrix, which guides the random walk to optimize an upstream objective. Unlike previous approaches to attention models, the method that we propose utilizes attention parameters exclusively on the data itself (e.g. on the random walk), and are not used by the model for inference. We experiment on link prediction tasks, as we aim to produce embeddings that best-preserve the graph structure, generalizing to unseen information. We improve state-of-the-art results on a comprehensive suite of real-world graph datasets including social, collaboration, and biological networks, where we observe that our graph attention model can reduce the error by up to 20\%-40\%. We show that our automatically-learned attention parameters can vary significantly per graph, and correspond to the optimal choice of hyper-parameter if we manually tune existing methods.

What our latest list of Climate Tech Companies to Watch says about this moment. On Monday, we published our 2025 edition of Climate Tech Companies to Watch . This marks the third time we've put the list together, and it's become one of my favorite projects to work on every year. In the journalism world, it's easy to get caught up in the latest news, whether it's a fundraising round, research paper, or startup failure. Curating this list gives our team a chance to take a step back and consider the broader picture. What industries are making progress or lagging behind?

A few EV makers in India went belly up after the government abruptly scaled back incentives and cracked down on the misuse of subsidies. Ather survived the storm and sales are increasing. More than 70% of the 200 million registered vehicles in India are two-wheelers. Ather Energy builds e-scooters for the rising middle class that could help commuters ditch highly-polluting, gas-guzzling models. While sales of Tesla or BYD cars drove electric vehicle adoption elsewhere in the world, two-wheelers have led the green energy transition in India. As one of the earliest "pure play" e-scooter makers, Ather Energy has helped drive micromobility EV penetration throughout India and boosted the shift away from carbon-emitting vehicles.

The startup is using waste materials and alternative fuels to make cement, slashing greenhouse gas emissions in a polluting industry. Cement is one of the most used materials on the planet, and the industry emits billions of tons of greenhouse gasses annually. Cemvision wants to use waste materials and alternative fuels to help reduce climate pollution from cement production. Today, making cement requires crushing limestone and heating it to super high temperatures, usually by burning fossil fuels. The chemical reactions also release carbon dioxide pollution. Swedish startup Cemvision made a few key production changes to reduce both emissions and the need to mine new materials.

And what distinguishes the firms that made the 2025 edition of our annual list of Climate Tech Companies to Watch. 's reporters and editors faced a dilemma as we began to mull nominees for this year's list of Climate Tech Companies to Watch. How do you pick companies poised to succeed in a moment of such deep uncertainty, at a time when the new Trump administration is downplaying the dangers of climate change, unraveling supportive policies for clean technologies, and enacting tariffs that will boost costs and disrupt supply chains for numerous industries? We as a publication are focused more on identifying companies developing technologies that can address the escalating threats of climate change, than on businesses positioned purely for market success. But we still don't want to lead our readers astray by highlighting a startup that winds up filing for bankruptcy six months later, even if its demise is due to a policy whiplash outside of its control. So we had to shift our thinking some.

Spain's Valencia region has been struck by more bad weather, a year after deadly floods killed more than 230 people there. A red alert has been put in place as Storm Gabrielle hits the region. Footage shows floodwater in parts of Valencia and Zaragoza, in the neighbouring Aragon region. The meteorological agency AEMET said between 160 and 200mm of rain had fallen in six to eight hours around the Ebro delta. No injuries have been reported, but schools, libraries and parks are closed in Valencia on Monday.

The new edition of our annual list features startups and established businesses working to decarbonize transportation, heavy industry, energy, and more. The need to cut emissions and adapt to our warming world is growing more urgent. This year, we've seen temperatures reach record highs, as they have nearly every year for the last decade . Climate-fueled natural disasters are affecting communities around the world, costing billions of dollars. That's why, for the past two years, has curated a list of companies with the potential to make a meaningful difference in addressing climate change (you can revisit the 2024 list here). We're excited to share that we'll publish our third edition of Climate Tech Companies to Watch on October 6.

Drone footage has captured a group of polar bears living inside an abandoned research station on Russia's Kolyuchin Island. Travel blogger, Vadim Makhorov, shared video that shows several bears inside the scattered building, looking through windows and walking around the island. A bear could be seen trying to catch the blogger's drone as it approached. The Kolyuchin weather station was abandoned in the early 1990s, after the collapse of the Soviet Union. Russian Alexey Molchanov breaks his own 2024 world record in one of the most technically challenging freediving events.