Government
Analyzing Intentional Behavior in Autonomous Agents under Uncertainty
Córdoba, Filip Cano, Judson, Samuel, Antonopoulos, Timos, Bjørner, Katrine, Shoemaker, Nicholas, Shapiro, Scott J., Piskac, Ruzica, Könighofer, Bettina
Principled accountability for autonomous decision-making in uncertain environments requires distinguishing intentional outcomes from negligent designs from actual accidents. We propose analyzing the behavior of autonomous agents through a quantitative measure of the evidence of intentional behavior. We model an uncertain environment as a Markov Decision Process (MDP). For a given scenario, we rely on probabilistic model checking to compute the ability of the agent to influence reaching a certain event. We call this the scope of agency. We say that there is evidence of intentional behavior if the scope of agency is high and the decisions of the agent are close to being optimal for reaching the event. Our method applies counterfactual reasoning to automatically generate relevant scenarios that can be analyzed to increase the confidence of our assessment. In a case study, we show how our method can distinguish between 'intentional' and 'accidental' traffic collisions.
Gender Neutralization for an Inclusive Machine Translation: from Theoretical Foundations to Open Challenges
Piergentili, Andrea, Fucci, Dennis, Savoldi, Beatrice, Bentivogli, Luisa, Negri, Matteo
Gender inclusivity in language technologies has become a prominent research topic. In this study, we explore gender-neutral translation (GNT) as a form of gender inclusivity and a goal to be achieved by machine translation (MT) models, which have been found to perpetuate gender bias and discrimination. Specifically, we focus on translation from English into Italian, a language pair representative of salient gender-related linguistic transfer problems. To define GNT, we review a selection of relevant institutional guidelines for gender-inclusive language, discuss its scenarios of use, and examine the technical challenges of performing GNT in MT, concluding with a discussion of potential solutions to encourage advancements toward greater inclusivity in MT.
IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces
Marchisio, Kelly, Verma, Neha, Duh, Kevin, Koehn, Philipp
The ability to extract high-quality translation dictionaries from monolingual word embedding spaces depends critically on the geometric similarity of the spaces -- their degree of "isomorphism." We address the root-cause of faulty cross-lingual mapping: that word embedding training resulted in the underlying spaces being non-isomorphic. We incorporate global measures of isomorphism directly into the Skip-gram loss function, successfully increasing the relative isomorphism of trained word embedding spaces and improving their ability to be mapped to a shared cross-lingual space. The result is improved bilingual lexicon induction in general data conditions, under domain mismatch, and with training algorithm dissimilarities. We release IsoVec at https://github.com/kellymarchisio/isovec.
Collaborative Learning for Cyberattack Detection in Blockchain Networks
Khoa, Tran Viet, Son, Do Hai, Hoang, Dinh Thai, Trung, Nguyen Linh, Quynh, Tran Thi Thuy, Nguyen, Diep N., Ha, Nguyen Viet, Dutkiewicz, Eryk
This article aims to study intrusion attacks and then develop a novel cyberattack detection framework for blockchain networks. Specifically, we first design and implement a blockchain network in our laboratory. This blockchain network will serve two purposes, i.e., to generate the real traffic data (including both normal data and attack data) for our learning models and implement real-time experiments to evaluate the performance of our proposed intrusion detection framework. To the best of our knowledge, this is the first dataset that is synthesized in a laboratory for cyberattacks in a blockchain network. We then propose a novel collaborative learning model that allows efficient deployment in the blockchain network to detect attacks. The main idea of the proposed learning model is to enable blockchain nodes to actively collect data, share the knowledge learned from its data, and then exchange the knowledge with other blockchain nodes in the network. In this way, we can not only leverage the knowledge from all the nodes in the network but also do not need to gather all raw data for training at a centralized node like conventional centralized learning solutions. Such a framework can also avoid the risk of exposing local data's privacy as well as the excessive network overhead/congestion. Both intensive simulations and real-time experiments clearly show that our proposed collaborative learning-based intrusion detection framework can achieve an accuracy of up to 97.7% in detecting attacks.
Must-do: What Congress has left on its plate at year's halfway mark
Fox News senior congressional correspondent Chad Pergram reports on the outcome of the debt limit bill and how both sides responded on'Your World.' There wasn't a lot Congress absolutely had to accomplish legislatively this year. And overall, the floor traffic will likely be light until fall. There are really only about five things which Congress must do this year. With the pages halfway off the calendar, lawmakers have taken care of two of the five.
How to Find the Most Accurate Weather Forecasting App
Although it may not seem like it, weather forecasts are better now than they've ever been. "Over the past 40 years, we've been adding an additional day of skill each decade," says David Novak, Director of the Weather Prediction Center at the U.S National Weather Service. In other words, forecasts made today about the weather five days from now are roughly as accurate as were weather forecasts made four days out in 2013. Government agencies, such as the U.S. National Weather Service and the U.K. Meteorological Office, run vast meteorological models on supercomputers. Improvements in forecast accuracy are mainly due to these models becoming larger, allowing them to use new sources of data and model the climate in greater detail.
What is behind Israel's major attack on Jenin?
Israel has launched one of its biggest attacks on the occupied West Bank, killing at least eight Palestinians in the Jenin refugee camp and wounding dozens more. The latest operation, ongoing on Monday, marks a significant escalation and follows a raid in Jenin two weeks ago that killed seven Palestinians and that was itself one of the largest conducted in years. Let's take a closer look at Israel's targeting of Jenin. The latest incursion into Jenin began on Sunday night with at least 10 air attacks in the densely-packed area, which houses some 14,000 displaced Palestinians in less than half a square kilometre (0.20sq mile). The attack included drone strikes and a missile, which damaged buildings and infrastructure, sending smoke billowing from the wreckage.
UN body discusses potential for deep sea mining, permits may be coming soon
Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. The International Seabed Authority -- the United Nations body that regulates the world's ocean floor -- is preparing to resume negotiations that could open the international seabed for mining, including for materials critical for the green energy transition. Years long negotiations are reaching a critical point where the authority will soon need to begin accepting mining permit applications, adding to worries over the potential impacts on sparsely researched marine ecosystems and habitats of the deep sea. Here's a look at what deep sea mining is, why some companies and countries are applying for permits to carry it out and why environmental activists are raising concerns.
Israel deploys thousands of troops, drones in attack on Jenin stronghold in terrorism 'hotspot'
Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. The Israeli military deployed thousands of troops and drones in an attack on a Palestinian militant stronghold in the West Bank on Sunday night. Military officials expect the roughly 2,000 troops to remain in the West Bank city of Jenin for up to 48 hours after launching the operation. Palestinian officials say at least eight people were killed and 50 were wounded in the attack, which was larger than any operation Israel has carried out this year.
The Download: lab-grown meat's climate impact, and Congress' AI plans
Soon, the menu in your favorite burger joint could include not only options made with meat, mushrooms, and black beans but also patties packed with lab-grown animal cells. Not only did the US just approve the sale of cultivated meat for the first time, but the industry is in the process of raising billions of dollars to bring its products to restaurants and grocery stores. In theory, that should be a big win for the climate--greenhouse-gas emissions from the animals we eat account for nearly 15% of the global total. But whether cultivated meat really is better for the environment is still not entirely clear. Two weeks ago, Senate majority leader Chuck Schumer announced his grand strategy for AI policymaking at a speech in Washington, DC, ushering in what might be a new era for US tech policy.