Deep neural networks (DNNs) have been broadly adopted in health risk prediction to provide healthcare diagnoses and treatments. To evaluate their robustness, existing research conducts adversarial attacks in the white/gray-box setting where model parameters are accessible. However, a more realistic black-box adversarial attack is ignored even though most real-world models are trained with private data and released as black-box services on the cloud. To fill this gap, we propose the first black-box adversarial attack method against health risk prediction models named MedAttacker to investigate their vulnerability. MedAttacker addresses the challenges brought by EHR data via two steps: hierarchical position selection which selects the attacked positions in a reinforcement learning (RL) framework and substitute selection which identifies substitute with a score-based principle. Particularly, by considering the temporal context inside EHRs, it initializes its RL position selection policy by using the contribution score of each visit and the saliency score of each code, which can be well integrated with the deterministic substitute selection process decided by the score changes. In experiments, MedAttacker consistently achieves the highest average success rate and even outperforms a recent white-box EHR adversarial attack technique in certain cases when attacking three advanced health risk prediction models in the black-box setting across multiple real-world datasets. In addition, based on the experiment results we include a discussion on defending EHR adversarial attacks.

Zero-shot cross-lingual transfer is an important feature in modern NLP models and architectures to support low-resource languages. In this work, We study zero-shot cross-lingual transfer from English to French and German under Multi-Label Text Classification, where we train a classifier using English training set, and we test using French and German test sets. We extend EURLEX57K dataset, the English dataset for topic classification of legal documents, with French and German official translation. We investigate the effect of using some training techniques, namely Gradual Unfreezing and Language Model finetuning, on the quality of zero-shot cross-lingual transfer. We find that Language model finetuning of multi-lingual pre-trained model (M-DistilBERT, M-BERT) leads to 32.0-34.94%, 76.15-87.54% relative improvement on French and German test sets correspondingly. Also, Gradual unfreezing of pre-trained model's layers during training results in relative improvement of 38-45% for French and 58-70% for German. Compared to training a model in Joint Training scheme using English, French and German training sets, zero-shot BERT-based classification model reaches 86% of the performance achieved by jointly-trained BERT-based classification model.

Today's battlefield environment is complex, dynamic and uncertain, and requires efficient support to ensure mission success. This relies on a proper support strategy to provide supported equipment able to fulfill the mission. In the context of defense where both systems and organization are complex, having a holistic approach is challenging by nature, forces and support agencies need to rely on an efficient decision support system. Logistics, readiness and sustainability are critical factors for asset management, which can benefit from AI to reach "Smart In Service" level relying especially on predictive and prescriptive approaches and on effective management of operational re-sources. Smart Support capacities can be then monitored by appropriate metrics and improved by multi-criteria decision support and knowledge management system.

Artificial Intelligence has been consistently one of the hottest topics year-round since the last decade. And there doesn't seem to be any sign of that changing anytime soon. Keeping that in mind, we have compiled a list of the TOP-10 stories that have been the talk of the town of 2021. So without further ado, here is the first one. Automating AI has been growing in popularity for the last few years.

Artificial intelligence (AI) helped the Air Force automate scheduling for the C-17 Globemaster III transport aircraft and improve scheduling accuracy rates by 92% last year, according to Air Force Chief Data Officer Eileen Vidrine. This is just one example of successes and use cases the Air Force has had as it develops data management strategies that inch the Defense Department as a whole closer to artificial intelligence capacities and closer to its target Joint All-Domain Command and Control (JADC2) initiative. DOD's efforts in AI has only grown in recent years, including establishing its Joint Artificial Intelligence Center (JAIC) in 2018. Coupled with recent announcements, the department is gearing up for further changes to its AI landscape. The Office of the Secretary of Defense (OSD) said Wednesday it is establishing a new Chief Digital and Artificial Intelligence Officer (CDAO) role to streamline AI efforts throughout DOD.

Mike Pondsmith started playing Dungeons & Dragons in the late seventies, as an undergraduate at the University of California, Davis. The game, published just a few years before, popularized a newish form of entertainment: tabletop role-playing, in which players, typically using dice and a set of rule books, create characters who pursue open-ended quests within an established world. "The most stimulating part of the game is the fact that anything can happen," an early D&D review noted. Soon, other such games hit the market, including Traveller, a sci-fi game published in 1977, the year that "Star Wars" came out. Pondsmith, a tall Black man who grew up in multiple countries because his dad was in the Air Force, loved sci-fi, and fancied himself a bit like Lando Calrissian, the smooth-talking "Star Wars" rogue played by Billy Dee Williams.

In any debate, there are always at least two sides. That reasoning also applies to whether or not it is a good idea to use artificial intelligence technology to try stemming the advantages of cybercriminals who are already using AI to improve their success ratio. In an email exchange, I asked Ramprakash Ramamoorthy, director of research at ManageEngine, a division of Zoho Corporation, for his thoughts on the matter. Ramamoorthy is firmly on the affirmative side for using AI to fight cybercrime. He said, "The only way to combat cybercriminals using AI-enhanced attacks is to fight fire with fire and employ AI countermeasures."

In the past two competitions, you predicted video popularity and viral tweets with data science, now it’s time for a whole new challenge! The first phase of this competition ends on 23rd December…

Late in 1966, in the sprawling computer lab of the Washington, D.C., office building that housed the United States Weather Bureau, Syukuro Manabe was waiting for a print job to finish. At stake was the fate of the planet. Manabe, who was thirty-five, had come to the U.S. from Japan almost a decade earlier. He managed a team of computer programmers, tasked with building a mathematical simulation of the planet's atmosphere. It had taken years to perfect, and cost millions of dollars. Now the simulation was complete.

Christmas Spirit Foundation executive director Rick Dungey on bringing cheer to military families and how viewers can help. The top U.S. commander for the Middle East said Thursday that the United States will keep the current 2,500 troops in Iraq for the foreseeable future, and he warned that he expects increasing attacks on U.S. and Iraqi personnel by Iranian-backed militias determined to get American forces out. Marine Gen. Frank McKenzie said in an interview with The Associated Press at the Pentagon that despite the shift by U.S. forces to a non-combat role in Iraq, they will still provide air support and other military aid for Iraq's fight against the Islamic State. Noting that Iranian-backed militias want all Western forces out of Iraq, he said an ongoing uptick in violence may continue through December. Gen. McKenzie, commander of the United States Central Command, testifies before the House Armed Services Committee on the conclusion of military operations in Afghanistan and plans for future counterterrorism operations on Wednesday, Sept. 29, 2021, on Capitol Hill in Washington.