PRESS-NEWS.org - Press Release Distribution
PRESS RELEASES DISTRIBUTION

Taking down human traffickers through online ads

Algorithm designed to spot anomalies in data finds new purpose in stopping trafficking

2021-04-22
(Press-News.org) Researchers at Carnegie Mellon University and McGill University have adapted an algorithm first developed to spot anomalies in data, like typos in patient information at hospitals or errant figures in accounting, to identify similarities across escort ads.

The algorithm scans and clusters similarities in text and could help law enforcement direct their investigations and better identify human traffickers and their victims, said Christos Faloutsos, the Fredkin Professor in Artificial Intelligence at CMU's School of Computer Science, who led the team.

"Our algorithm can put the millions of advertisements together and highlight the common parts," Faloutsos said. "If they have a lot of things in common, it's not guaranteed, but it's highly likely that it is something suspicious."

The team calls the algorithm InfoShield and presented a paper on their findings at this year's IEEE International Conference on Data Engineering (ICDE).

According to the International Labor Organization, an estimated 24.9 million people are trapped in forced labor. Of those, 55% are women and girls trafficked in the commercial sex industry, where most ads are posted online. The same person may write ads for four to six victims, leading to similar phrasing and duplication among listings.

"Human trafficking is a dangerous societal problem which is difficult to tackle," lead authors Catalina Vajiac and Meng-Chieh Lee wrote. "By looking for small clusters of ads that contain similar phrasing rather than analyzing standalone ads, we're finding the groups of ads that are most likely to be organized activity, which is a strong signal of (human trafficking)."

To test InfoShield, the team ran it on a set of escort listings in which experts had already identified trafficking ads. The team found that InfoShield outperformed other algorithms at identifying the trafficking ads, flagging them with 85% precision. Perhaps more importantly, it did not incorrectly flag any escort listings as human trafficking ads when they were not. False positives can quickly erode trust in an algorithm, Faloutsos said.

Proving this success was tricky. The test data set contained actual ads placed by human traffickers. The information in these ads is sensitive and kept private to protect the victims of human trafficking, so the team could not publish examples of the similarities identified or the data set itself. This meant that other researchers could not verify their work.

"We were basically saying, 'Trust us, our algorithm works,'" Vajiac said.

To remedy this, the team looked for public data sets they could use to test InfoShield that mimicked what the algorithm looked for in human trafficking data: text and the similarities in it. They turned to Twitter, where they found a trove of text and similarities in that text created by bots.

Bots will often tweet the same information in similar ways. Like a human trafficking ad, the format of a bot tweet might be the same with some pieces of information changed. Rabbany said that in both cases -- Twitter bots and human trafficking ads -- the goal is to find organized activity.

Among tweets, InfoShield outperformed other state-of-the-art algorithms at detecting bots. Vajiac said this finding was a surprise, given that other algorithms take into account Twitter-specific metrics such as the number of followers, retweets and likes, and InfoShield did not. The algorithm instead relied solely on the text of the tweets to determine bot or not.

"That speaks a lot to how important text is in finding these types of organizations," Vajiac said.

INFORMATION:

The paper's authors are Christos Faloutos, Catalina Vajiac and Namyong Park from Carnegie Mellon University; Reihaneh Rabbany, Aayushi Kulshrestha and Sacha Levy from McGill University, Meng-Chieh Lee from National Chiao Tung University; and Cara Jones from Marinus Analytics.



ELSE PRESS RELEASES FROM THIS DATE:

Life satisfaction among young people linked to collectivism

2021-04-22
An international group of scientists from Italy, the USA, China and Russia have studied the relationship between collectivism, individualism and life satisfaction among young people aged 18-25 in four countries. They found that the higher the index of individualistic values at the country level, the higher the life satisfaction of young people's lives. At the individual level, however, collectivism was more significant for young people. In all countries, young people found a positive association between collectivism, particularly with regard to family ties, and life satisfaction. This somewhat contradicts and at the same time clarifies the results ...

Use of e-cigarettes plus tobacco cigarettes linked to higher risk of respiratory symptoms

2021-04-22
BOSTON - Exclusively using (or "vaping") e-cigarettes can help people quit smoking, but many people using e-cigarettes to quit smoking continue to smoke cigarettes. New research led by investigators at Massachusetts General Hospital (MGH) reveals that respiratory symptoms--such as cough and wheeze--are more likely to develop when people use both e-cigarettes and tobacco cigarettes together compared with using either one alone. The findings are published in the American Journal of Respiratory and Critical Care Medicine, the flagship journal of the American Thoracic Society. The ...

Ancient Indigenous forest gardens promote a healthy ecosystem: SFU study

Ancient Indigenous forest gardens promote a healthy ecosystem: SFU study
2021-04-22
A new study by Simon Fraser University historical ecologists finds that Indigenous-managed forests--cared for as "forest gardens"--contain more biologically and functionally diverse species than surrounding conifer-dominated forests and create important habitat for animals and pollinators. The findings are published today in Ecology and Society. According to researchers, ancient forests were once tended by Ts'msyen and Coast Salish peoples living along the north and south Pacific coast. These forest gardens continue to grow at remote archaeological villages on Canada's northwest coast and are composed ...

Hungry fruit flies are extreme ultramarathon fliers

Hungry fruit flies are extreme ultramarathon fliers
2021-04-22
In 2005, an ultramarathon runner ran continuously 560 kilometers (350 miles) in 80 hours, without sleeping or stopping. This distance was roughly 324,000 times the runner's body length. Yet this extreme feat pales in comparison to the relative distances that fruit flies can travel in a single flight, according to new research from Caltech. Caltech scientists have now discovered that fruit flies can fly up to 15 kilometers (about 9 miles) in a single journey--6 million times their body length, or the equivalent of over 10,000 kilometers for the average human. In comparison to body length, this is further than many migratory species of birds can fly in a day. To discover this, the team conducted experiments in a dry lakebed ...

Pregnant women with COVID-19 face high mortality rate

2021-04-22
In a worldwide study of 2,100 pregnant women, those who contracted COVID-19 during pregnancy were 20 times more likely to die than those who did not contract the virus. UW Medicine and University of Oxford doctors led this first-of-its-kind study, published today in JAMA Pediatrics. The investigation involved more than 100 researchers and pregnant women from 43 maternity hospitals in 18 low-, middle- and high-income nations; 220 of the women received care in the United States, 40 at UW Medicine. The research was conducted between April and August of 2020. The study is unique because each woman affected by COVID-19 was compared with two uninfected pregnant women who gave birth during the same span in the same hospital. Aside ...

Machine learning model generates realistic seismic waveforms

Machine learning model generates realistic seismic waveforms
2021-04-22
LOS ALAMOS, N.M., April 22, 2021--A new machine-learning model that generates realistic seismic waveforms will reduce manual labor and improve earthquake detection, according to a study published recently in JGR Solid Earth. "To verify the e?cacy of our generative model, we applied it to seismic ?eld data collected in Oklahoma," said Youzuo Lin, a computational scientist in Los Alamos National Laboratory's Geophysics group and principal investigator of the project. "Through a sequence of qualitative and quantitative tests and benchmarks, we saw that our model can generate high-quality synthetic waveforms and improve machine learning-based earthquake detection algorithms." Quickly and accurately detecting earthquakes can be a challenging task. Visual detection done ...

Study paves the way for new photosensitive materials

Study paves the way for new photosensitive materials
2021-04-22
Photocatalysts are useful materials, with a myriad of environmental and energy applications, including air purification, water treatment, self-cleaning surfaces, pollution-fighting paints and coatings, hydrogen production and CO2 conversion to sustainable fuels. An efficient photocatalyst converts light energy into chemical energy and provides this energy to a reacting substance, to help chemical reactions occur. One of the most useful such materials is knows as titanium oxide or titania, much sought after for its stability, effectiveness as a photocatalyst ...

Reprogramming fibroblasts could result in scar-free wound healing, suggests study in mice

2021-04-22
Researchers have determined a way to potentially minimize or eliminate scarring in wounded skin, by further decoding the scar-promoting role of a specific class of dermal fibroblast cells in mice. By preventing these cells from expressing the transcription factor Engrailed-1 (En-1), Shamik Mascharak and colleagues reprogrammed these cells to take on a different identity, capable of regenerating wounded skin - including the restoration of structures such as hair follicles and sweat glands that are absent in scarred skin tissue. With further development and testing, their discovery could lead to therapies to reduce or completely avoid scarring ...

China requires switch to zero-carbon energy to achieve more ambitious Paris Agreement goal, models S

2021-04-22
A new multi-model analysis suggests that China will need to reduce its carbon emissions by over 90% and its energy consumption by almost 40%, in order to meet the more ambitious target set by the 2016 Paris Agreement. The Agreement called for no more than a 1.5°Celsius (C) global temperature rise by 2050. These results provide a clear directive for China to deploy multiple strategies at once for long-term emission mitigation, the authors say. The findings also highlight the need for more research on the economic consequences of working toward a 1.5°C warming limit, arguing that current studies are far from adequate to inform the sixth assessment report (AR 6) on climate change planned for release by the United Nations' Intergovernmental ...

Medical record analysis links cannabis use disorder in pregnancy to infant health problems

2021-04-22
A new study of nearly five million live births recorded in California from 2001 to 2012 found that babies born to mothers diagnosed with cannabis use disorders at delivery were more likely to experience negative health outcomes, including preterm birth and low birth weight, compared to babies born to mothers without a cannabis use disorder diagnosis. The analysis, published today in Addiction and funded by the National Institute on Drug Abuse (NIDA), part of the National Institutes of Health, adds to a growing body of evidence that prenatal exposure to cannabis (marijuana) may be associated with poor birth outcomes, and sheds light on infant health one year after birth. Recent studies have shown the ...

LAST 30 PRESS RELEASES:

Study unexpectedly finds living in rural, rather than urban environments in first five years of life could be a risk factor for developing type 1 diabetes

Editorial urges deeper focus on heart-lung interactions in pulmonary vascular disease

Five University of Tennessee faculty receive Fulbright Awards

5 advances to protect water sources, availability

OU Scholar awarded Fulbright for Soviet cinema research

Brain might become target of new type 1 diabetes treatments

‘Shore Wars:’ New research aims to resolve coastal conflict between oysters and mangroves, aiding restoration efforts

Why do symptoms linger in some people after an infection? A conversation on post-acute infection syndromes

Study reveals hidden drivers of asthma flare-ups in children

Physicists decode mysterious membrane behavior

New insights about brain receptor may pave way for next-gen mental health drugs

Melanoma ‘sat-nav’ discovery could help curb metastasis

When immune commanders misfire: new insights into rheumatoid arthritis inflammation

SFU researchers develop a new tool that brings blender-like lighting control to any photograph

Pups in tow, Yellowstone-area wolves trek long distances to stay near prey

AI breakthrough unlocks 'new' materials to replace lithium-ion batteries

Making molecules make sense: A regional explanation method reveals structure–property relationships

Partisan hostility, not just policy, drives U.S. protests

The Journal of Nuclear Medicine Ahead-of-Print Tip Sheet: August 1, 2025

Young human blood serum factors show potential to rejuvenate skin through bone marrow

Large language models reshape the future of task planning

Narrower coverage of MS drugs tied to higher relapse risk

Researchers harness AI-powered protein design to enhance T-cell based immunotherapies

Smartphone engagement during school hours among US youths

Online reviews of health care facilities

MS may begin far earlier than previously thought

New AI tool learns to read medical images with far less data

Announcing XPRIZE Healthspan as Tier 5 Sponsor of ARDD 2025

Announcing Immortal Dragons as Tier 4 Sponsor of ARDD 2025

Reporting guideline for chatbot health advice studies

[Press-News.org] Taking down human traffickers through online ads
Algorithm designed to spot anomalies in data finds new purpose in stopping trafficking