In recent years, deep neural networks (DNNs) have witnessed extensive applications, and protecting their intellectual property (IP) is thus crucial. As a non-invasive way for model IP protection, model fingerprinting has become popular. However, existing single-point based fingerprinting methods are highly sensitive to the changes in the decision boundary, and may suffer from the misjudgment of the resemblance of sparse fingerprinting, yielding high false positives of innocent models. In this paper, we propose ADV-TRA, a more robust fingerprinting scheme that utilizes adversarial trajectories to verify the ownership of DNN models. Benefited from the intrinsic progressively adversarial level, the trajectory is capable of tolerating greater degree of alteration in decision boundaries.

In natural language processing and vision, pretraining is utilized to learn effective representations. Unfortunately, the success of pretraining does not easily carry over to time series due to potential mismatch between sources and target. Actually, common belief is that multi-dataset pretraining does not work for time series! Au contraire, we introduce a new self-supervised contrastive pretraining approach to learn one encoding from many unlabeled and diverse time series datasets, so that the single learned representation can then be reused in several target domains for, say, classification. Specifically, we propose the XD-MixUp interpolation method and the Soft Interpolation Contextual Contrasting (SICC) loss. Empirically, this outperforms both supervised training and other self-supervised pretraining methods when finetuning on low-data regimes. This disproves the common belief: We can actually learn from multiple time series datasets, even from 75 at once.

"I have never seen another instance like this in my career," said Bradley Tusk, a venture capitalist and political consultant. It has permeated absolutely everything." Silicon Valley tech workers have long been regarded as liberal but not politically overactive. After President Trump's victory in 2016, however, workers at large tech companies such as Google and Amazon began agitating more on issues like the ethics of artificial intelligence, immigration and climate change. Now many start-up workers, who have been sold on a mission of changing the world, expect their employers to support their social and political causes, entrepreneurs and investors said.

As humans, we love contrast. It is no wonder that experts, while defining the impact of Artificial Intelligence (AI) on the future of humankind, are at two ends of the spectrum. One is a happy scenario of human beings and artificially intelligent machines coexisting in perfect harmony. Another is an Orwellian dystopia of AI dominance over human intelligence and civilization. While there may be disagreements about the future, everyone agrees on the impact and growing ubiquity of AI.

Like Rome, query understanding can't be built in one day. Implementing holistic understanding, reductionist understanding, and resolution is a lot of work, and as a search team you can always find room to improve all of these. But if you're not already looking at query understanding in this framework -- or if you're not looking at query understanding at all -- I urge you to consider it. It won't reduce the challenges, but it will help you tackle them in stages.