The statistical modeling of random networks has been widely used to uncover interaction mechanisms in complex systems and to predict unobserved links in real-world networks. In many applications, network connections are collected via egocentric sampling: a subset of nodes is sampled first, after which all links involving this subset are recorded; all other information is missing. Compared with the assumption of ``uniformly missing at random", egocentrically sampled partial networks require specially designed modeling strategies. Current statistical methods are either computationally infeasible or based on intuitive designs without theoretical justification. Here, we propose an approach to fit general low-rank models for egocentrically sampled networks, which include several popular network models. This method is based on graph spectral properties and is computationally efficient for large-scale networks. It results in consistent recovery of missing subnetworks due to egocentric sampling for sparse networks. To our knowledge, this method offers the first theoretical guarantee for egocentric partial network estimation in the scope of low-rank models. We evaluate the technique on several synthetic and real-world networks and show that it delivers competitive performance in link prediction tasks.

Deep Learning (DL) is being applied in various domains, especially in safety-critical applications such as autonomous driving. Consequently, it is of great significance to ensure the robustness of these methods and thus counteract uncertain behaviors caused by adversarial attacks. In this paper, we use gradient heatmaps to analyze the response characteristics of the VGG-16 model when the input images are mixed with adversarial noise and statistically similar Gaussian random noise. In particular, we compare the network response layer by layer to determine where errors occurred. Several interesting findings are derived. First, compared to Gaussian random noise, intentionally generated adversarial noise causes severe behavior deviation by distracting the area of concentration in the networks. Second, in many cases, adversarial examples only need to compromise a few intermediate blocks to mislead the final decision. Third, our experiments revealed that specific blocks are more vulnerable and easier to exploit by adversarial examples. Finally, we demonstrate that the layers $Block4\_conv1$ and $Block5\_cov1$ of the VGG-16 model are more susceptible to adversarial attacks. Our work could provide valuable insights into developing more reliable Deep Neural Network (DNN) models.

This paper addresses the problem of set-to-set matching, which involves matching two different sets of items based on some criteria, especially in the case of high-dimensional items like images. Although neural networks have been applied to solve this problem, most machine learning-based approaches assume that the training and test data follow the same distribution, which is not always true in real-world scenarios. To address this limitation, we introduce SHIFT15M, a dataset that can be used to evaluate set-to-set matching models when the distribution of data changes between training and testing. We conduct benchmark experiments that demonstrate the performance drop of naive methods due to distribution shift. Additionally, we provide software to handle the SHIFT15M dataset in a simple manner, with the URL for the software to be made available after publication of this manuscript. We believe proposed SHIFT15M dataset provide a valuable resource for evaluating set-to-set matching models under the distribution shift.

Within recent times, cybercriminals have curated a variety of organised and resolute cyber attacks within a range of cyber systems, leading to consequential ramifications to private and governmental institutions. Current security-based automation and orchestrations focus on automating fixed purpose and hard-coded solutions, which are easily surpassed by modern-day cyber attacks. Research within Automated Cyber Defence will allow the development and enabling intelligence response by autonomously defending networked systems through sequential decision-making agents. This article comprehensively elaborates the developments within Automated Cyber Defence through a requirement analysis divided into two sub-areas, namely, automated defence and attack agents and Autonomous Cyber Operation (ACO) Gyms. The requirement analysis allows the comparison of automated agents and highlights the importance of ACO Gyms for their continual development. The requirement analysis is also used to critique ACO Gyms with an overall aim to develop them for deploying automated agents within real-world networked systems. Relevant future challenges were addressed from the overall analysis to accelerate development within the area of Automated Cyber Defence.

Auditing large language models for unexpected behaviors is critical to preempt catastrophic deployments, yet remains challenging. In this work, we cast auditing as an optimization problem, where we automatically search for input-output pairs that match a desired target behavior. For example, we might aim to find a non-toxic input that starts with "Barack Obama" that a model maps to a toxic output. This optimization problem is difficult to solve as the set of feasible points is sparse, the space is discrete, and the language models we audit are non-linear and high-dimensional. To combat these challenges, we introduce a discrete optimization algorithm, ARCA, that jointly and efficiently optimizes over inputs and outputs. Our approach automatically uncovers derogatory completions about celebrities (e.g. "Barack Obama is a legalized unborn" -> "child murderer"), produces French inputs that complete to English outputs, and finds inputs that generate a specific name. Our work offers a promising new tool to uncover models' failure-modes before deployment.

Biometric technology may make it easy to unlock your phone, but democratic lawmakers have long cautioned against the use of facial recognition and biometrics by law enforcement. Not only have researchers documented instances of racial and gender bias in such systems, false positives have even led to real instances of wrongful arrest. That's why lawmakers have re-introduced the Facial Recognition and Biometric Technology Act. This actually marks the third time the bill was introduced to the Senate -- despite being introduced in 2020 and 2021, the act was never advanced to a vote. If passed, the Facial Recognition and Biometric Technology Act would outright ban any use of facial recognition or biometric surveillance by the federal government unless that use is explicitly approved by an Act of Congress.

Despite advances that have been made in women's participation in technology education and innovation over the past decade, women remain under-represented in the information technology (IT) sector and in IT-based entrepreneurial initiatives. The 2019 report I'd blush if I could published by the UNSECO is striking. It found that only 12 per cent of artificial intelligence (AI) researchers and just six percent of professional software developers are women. Without diverse perspectives and ideas, we risk developing new technologies that do not meet the needs of half the population. In fact, the European Commission's 2020 white paper into AI calls for "requirements to take reasonable measures aimed at ensuring that [the] use of AI systems does not lead to outcomes entailing prohibited discrimination."

‘AI will soon be the king of the sky,’ scientists say after artificial intelligence machine shows superior performance in cutting-edge close-range combat.

Romanian Prime Minister Nicolae Ciucă has announced that he is the first political leader in the world to receive advice from an AI consultant. The mirror-shaped bot called ION was developed by Romanian researchers. Ciucă said that thanks to Ion, he could quickly respond to the'opinions and demands' of the Romanians. Romanian Prime Minister Nicolae Ciucă surprised his cabinet by introducing a new member powered entirely by artificial intelligence. To show his fellow ministers how this works, Ciucă organized a small demonstration called "Ion", his new "mirror-looking" honorary adviser. Ion gave a voice response to the Prime Minister's commands, the answers were written on the mirror.

Belarus has detained several people over what it calls an attempted act of sabotage at a Belarusian airfield, President Alexander Lukashenko was cited as saying. Belarusian anti-government activists said last month that they had blown up a sophisticated Russian military aircraft – a Beriev A-50 surveillance plane – in a drone attack at an airfield near the Belarusian capital Minsk, a claim disputed by Moscow and Minsk. "To date, more than 20 accomplices who are in Belarus have been detained. The rest are hiding," said Lukashenko, a key Kremlin ally, according to state news agency Belta. He identified the presumed main culprit as a dual national of Ukraine and Russia.