Adversarial attacks on tabular data present unique challenges due to the heterogeneous nature of mixed categorical and numerical features. Unlike images where pixel perturbations maintain visual similarity, tabular data lacks intuitive similarity metrics, making it difficult to define imperceptible modifications. Additionally, traditional gradient-based methods prioritise $\ell_p$-norm constraints, often producing adversarial examples that deviate from the original data distributions. To address this, we propose a latent-space perturbation framework using a mixed-input Variational Autoencoder (VAE) to generate statistically consistent adversarial examples. The proposed VAE integrates categorical embeddings and numerical features into a unified latent manifold, enabling perturbations that preserve statistical consistency. We introduce In-Distribution Success Rate (IDSR) to jointly evaluate attack effectiveness and distributional alignment. Evaluation across six publicly available datasets and three model architectures demonstrates that our method achieves substantially lower outlier rates and more consistent performance compared to traditional input-space attacks and other VAE-based methods adapted from image domain approaches, achieving substantially lower outlier rates and higher IDSR across six datasets and three model architectures. Our comprehensive analyses of hyperparameter sensitivity, sparsity control, and generative architecture demonstrate that the effectiveness of VAE-based attacks depends strongly on reconstruction quality and the availability of sufficient training data. When these conditions are met, the proposed framework achieves superior practical utility and stability compared with input-space methods. This work underscores the importance of maintaining on-manifold perturbations for generating realistic and robust adversarial examples in tabular domains.

Rubio hails'tremendous progress' at Ukraine peace talks A tremendous amount of progress has been achieved in talks to finalise a US-proposed peace plan to end the Russia-Ukraine war, Secretary of State Marco Rubio has said. But there's still some work to be done, Rubio said after meeting Ukrainian and European negotiators in Geneva, Switzerland. Ukrainian President Volodymyr Zelensky said there were signals that President [Donald] Trump's team is hearing us. Ukraine and its European allies had expressed concern over the leaked proposals, seen as favouring Russia and welcomed by Vladimir Putin as the basis for settlement. Zelensky had said Ukraine might face a very difficult choice: either losing dignity, or risk losing a key partner.

How can you tell if your new favourite artist is a real person? There's a new song doing the rounds, and in the immortal words of Kylie Minogue, you just can't get it out of your head. But what if it was created by a robot, or the artist themself is a product of artificial intelligence (AI)? Do streaming sites have an obligation to label music as AI-generated? And does it even matter, if you like what you hear?

The incredible offer appeared to loyalty card holders of the European electronics chain on November 8. After 11 days the company began contacting buyers, calling it a clear mistake. Italian electronics retailer MediaWorld has scrambled to fix a world-historic iPad pricing error. On November 8, an offer for loyalty card holders appeared on the website of MediaWorld, a European electronics retailer. No catch, no strings attached.

Using Jmail, you can read thousands of Jeffrey Epstein's emails in a familiar format. Use the star function to highlight notable finds. Last week, the House Committee on Oversight and Government Reform released 20,000 documents from the estate of registered sex offender and disgraced financier Jeffrey Epstein . They included thousands of emails sent between Epstein and high-profile people like Epstein confidant Ghislaine Maxwell, political strategist Steve Bannon, journalist Michael Wolff, and former US treasury secretary Larry Summers, as well as revealing text messages . Many of them allude or directly refer to president Donald Trump.

Neural Information Processing Systems http://nips.cc/

The Posha and the Thermomix TM7 are the closest things to a home robot chef that mere mortals can afford. The catch is that you're the prep cook. The holiday is still almost a week away, and I'm sick of Thanksgiving. I've already made four rounds of mashed potatoes, three of mac and cheese, and three turkeys (with more still waiting in my fridge) as part of testing smart probes to help smoke turkeys outside and preparing seven-course holiday meal kits for friends and family. I was eager to finally outsource some of the cooking by testing two very different robo-chef devices, the Thermomix TM7 and the Posha kitchen robot . Both promise to plan my meals and also do most of the cooking, which sounds pretty good to me. The Thermomix descends from a German device launched in 1968--a time when the best-known robot chef was cartoon Rosie on --that was essentially a blender with a heater. It's since caught on big in countries from Italy to Portugal to Australia, and over the years it's added multi-tier steaming, baking, proofing, a touchscreen, an encyclopedic recipe app, and a whole lot of smart features.

Privacy preserving is an important issue in learning.

Neural Information Processing Systems http://nips.cc/

Many physical processes, however, generate data that are continuous but non-Gaussian.