Deep neural networks (DNNs) are widely used models for investigating biological visual representations. However, existing DNNs are mostly designed to analyze neural responses to static images, relying on feedforward structures and lacking physiological neuronal mechanisms. There is limited insight into how the visual cortex represents natural movie stimuli that contain context-rich information. To address these problems, this work proposes the long-range feedback spiking network (LoRaFB-SNet), which mimics top-down connections between cortical regions and incorporates spike information processing mechanisms inherent to biological neurons. Taking into account the temporal dependence of representations under movie stimuli, we present Time-Series Representational Similarity Analysis (TSRSA) to measure the similarity between model representations and visual cortical representations of mice. LoRaFB-SNet exhibits the highest level of representational similarity, outperforming other well-known and leading alternatives across various experimental paradigms, especially when representing long movie stimuli. We further conduct experiments to quantify how temporal structures (dynamic information) and static textures (static information) of the movie stimuli influence representational similarity, suggesting that our model benefits from long-range feedback to encode context-dependent representations just like the brain. Altogether, LoRaFB-SNet is highly competent in capturing both dynamic and static representations of the mouse visual cortex and contributes to the understanding of movie processing mechanisms of the visual system.

Defense Department says Anthropic poses'unacceptable risk' to national security The Pentagon has submitted a court filing in response to Anthropic's lawsuit challenging its'supply chain risk' designation. The Department of Defense said giving Anthropic continued access to its warfighting infrastructure would "introduce unacceptable risk" to its supply chains in a court filing submitted in response to the AI company's lawsuit. If you'll recall, Anthropic sued the government to challenge the supply chain risk designation it received for refusing to allow its model to be used for mass surveillance and the development of autonomous weapons. In its filing, the department explained that its secretary, Pete Hegseth, had a provision incorporated into AI service contracts, allowing the agency to use their technologies for any lawful purpose. Anthropic refused its terms and apparently, the company's behavior caused the Pentagon to question whether it truly was a "trusted partner" that it could work with when it comes to "highly sensitive" initiatives.

How do you know if your data is fair? And if it isn't, what can you do about it? Machine learning models are increasingly used to make high-stakes decisions, from predicting who gets a loan to estimating the likelihood that someone will reoffend. But these models are only as good as the data they learn from [Shahbazi 2023]. If the training data is biased, the model's decisions will likely be biased too [Hort 2024, Pagano 2023].

Charles Bennett and Gilles Brassard pioneered quantum information theory. Now they've been awarded the highest honor in computer science. Today it's widely acknowledged that the future of computing will involve the quantum realm . Companies like Google, Microsoft, IBM, and a few well-funded startups are frantically building quantum computers and routinely claiming advances that seem to bring this exotic, world-changing technology within reach. In 1979 all of this was unthinkable.

Do Taliban's drone attacks expose a chink in Pakistan's armour? On the evening of March 13, drones struck three locations across Pakistan. Two children were wounded in Quetta. Civilians were also injured in Kohat and in Rawalpindi, the garrison city that houses the headquarters of Pakistan's armed forces and neighbours the capital, Islamabad. Pakistan's military said the drones were intercepted before reaching their targets.

Importantly, this matches the optimal bound $G\|w_\star\|\sqrt{T}$ available with such knowledge (up to logarithmic factors), unless either $\|w_\star\|$ or $G$ is so large that even $G\|w_\star\|\sqrt{T}$ is roughly linear in $T$. Thus, at a high level it matches the optimal bound in all cases in which one can achieve sublinear regret.

Iran war: What is happening on day 19 of US-Israel attacks? Iran has pledged "revenge" after Israeli strikes killed security chief Ali Larijani and commander of Basij paramilitary forces Gholamreza Soleimani, with Foreign Minister Abbas Araghchi saying Tehran's political system remains strong as the war entered its 19th day . Iran launched more attacks on Israel, causing extensive property damage, after an earlier strike killed two people in Ramat Gan. Political tensions are also rising in the United States, as senior counterterrorism official Joe Kent resigned, saying "we started this war due to pressure from Israel and its powerful American lobby". Meanwhile, President Donald Trump criticised NATO allies and partners for failing to provide stronger military support in efforts to end Iran's chokehold on the Strait of Hormuz.

Machine learning methods have a groundbreaking impact in many application domains, but their application on real robotic platforms is still limited.Despite the many challenges associated with combining machine learning technology with robotics, robot learning remains one of the most promising directions for enhancing the capabilities of robots. When deploying learning-based approaches on real robots, extra effort is required to address the challenges posed by various real-world factors. To investigate the key factors influencing real-world deployment and to encourage original solutions from different researchers, we organized the Robot Air Hockey Challenge at the NeurIPS 2023 conference. We selected the air hockey task as a benchmark, encompassing low-level robotics problems and high-level tactics. Different from other machine learning-centric benchmarks, participants need to tackle practical challenges in robotics, such as the sim-to-real gap, low-level control issues, safety problems, real-time requirements, and the limited availability of real-world data. Furthermore, we focus on a dynamic environment, removing the typical assumption of quasi-static motions of other real-world benchmarks.The competition's results show that solutions combining learning-based approaches with prior knowledge outperform those relying solely on data when real-world deployment is challenging.Our ablation study reveals which real-world factors may be overlooked when building a learning-based solution.The successful real-world air hockey deployment of best-performing agents sets the foundation for future competitions and follow-up research directions.

Large Language Models (LLMs) are recognized for their potential to be an important building block toward achieving artificial general intelligence due to their unprecedented capability for solving diverse tasks. Despite these achievements, LLMs often underperform in domain-specific tasks without training on relevant domain data. This phenomenon, which is often attributed to distribution shifts, makes adapting pre-trained LLMs with domain-specific data crucial. However, this adaptation raises significant privacy concerns, especially when the data involved come from sensitive domains. In this work, we extensively investigate the privacy vulnerabilities of adapted (fine-tuned) LLMs and benchmark privacy leakage across a wide range of data modalities, state-of-the-art privacy attack methods, adaptation techniques, and model architectures. We systematically evaluate and pinpoint critical factors related to privacy leakage. With our organized codebase and actionable insights, we aim to provide a standardized auditing tool for practitioners seeking to deploy customized LLM applications with faithful privacy assessments.

Collecting training data from untrusted sources exposes machine learning services to poisoning adversaries, who maliciously manipulate training data to degrade the model accuracy. When trained on offline datasets, poisoning adversaries have to inject the poisoned data in advance before training, and the order of feeding these poisoned batches into the model is stochastic. In contrast, practical systems are more usually trained/fine-tuned on sequentially captured real-time data, in which case poisoning adversaries could dynamically poison each data batch according to the current model state. In this paper, we focus on the real-time settings and propose a new attacking strategy, which affiliates an accumulative phase with poisoning attacks to secretly (i.e., without affecting accuracy) magnify the destructive effect of a (poisoned) trigger batch. By mimicking online learning and federated learning on MNIST and CIFAR-10, we show that model accuracy significantly drops by a single update step on the trigger batch after the accumulative phase. Our work validates that a well-designed but straightforward attacking strategy can dramatically amplify the poisoning effects, with no need to explore complex techniques.