Post Tagged with: "predictive analytics"

Using Speech Patterns to Detect Psychopaths

Using Speech Patterns to Detect Psychopaths

Hannibal

With regard to psychopaths, “We think the ‘uhs’ and ‘ums’ are about putting the mask of sanity on,” Hancock told LiveScience.

Psychopaths appear to view the world and others instrumentally, as theirs for the taking, the team, which also included Stephen Porter from the University of British Columbia, wrote.

As they expected, the psychopaths’ language contained more words known as subordinating conjunctions. These words, including “because” and “so that,” are associated with cause-and-effect statements.

“This pattern suggested that psychopaths were more likely to view the crime as the logical outcome of a plan (something that ‘had’ to be done to achieve a goal),” the authors write.

And finally, while most of us respond to higher-level needs, such as family, religion or spirituality, and self-esteem, psychopaths remain occupied with those needs associated with a more basic existence.

MSNBC: How to spot psychopaths: Speech patterns give them away

Bruce Schneier writes: “I worry about people being judged by these criteria. Psychopaths make up about 1% of the population, so even a small false-positive rate can be a significant problem.”

See also: The Rise of Predictive Policing: Police Using Statistics to Predict Crime

November 22, 2011 1 comment
The CIA Using Sentiment Analysis to Gauge Regional Stability

The CIA Using Sentiment Analysis to Gauge Regional Stability

human geopolitical chess

From The Atlantic:

How stable is China? What are people discussing and thinking in Pakistan? To answer these sorts of question, the U.S. government has turned to a rich source: social media.

The Associated Press reports that the CIA maintains a social-media tracking center operated out of an nondescript building in a Virginia industrial park. The intelligence analysts at the agency’s Open Source Center, who other agents refer to as “vengeful librarians,” are tasked with sifting through millions of tweets, Facebook messages, online chat logs, and other public data on the World Wide Web to glean insights into the collective moods of regions or groups abroad. According to the Associated Press, these librarians are tracking up to five million tweets a day from places like China, Pakistan and Egypt.

The Atlantic: How The CIA Uses Social Media to Track How People Feel

See also: Predicting the future with Twitter.

November 8, 2011 0 comments
The Rise of Predictive Policing: Police Using Statistics to Predict Crime

The Rise of Predictive Policing: Police Using Statistics to Predict Crime

The Minority Report

The Department of Homeland security is field testing a system that will attempt to predict which passengers on an airline are planning terrorist activity, according to Nature. The system, called Future Attribute Screening Technology (FAST) looks at a number of factors, including your pulse, the steadiness of your gaze and the way you walk and calculates the probability that you’re planning to commit a crime. It’s a bit like a polygraph, but it doesn’t require subjects to be connecting to a polygraph.

DHS claims that the system is 70% effective in lab tests.

Nature: Terrorist ‘pre-crime’ detector field tested in United States

But DHS isn’t the only law enforcement agency looking to statistic modeling to predict crime. Earlier this year Slate ran a story on how police departments, including the LAPD and Chicago PD, are researching predictive policing. This projects aren’t about predicting the actions of one individual, Minority Report style, but instead are designed to help decide how best to allocate police resources.

Slate: Can police really predict crime before it happens?.

June 6, 2011 2 comments
Inside the World of Wannabe Cyberspooks for Hire

Inside the World of Wannabe Cyberspooks for Hire

Many of you have probably heard about the internal e-mails from the security firm HBGary. Ars Technica summarizes much of it in a length article, including HBGary’s aspirations to provide various PSYOPS services – such as cartoons and social media propaganda management – to federal agencies. Ars Technica details one proposal the firm sent to DARPA, which agency declined to fund:

So Barr and Hoglund drafted a plan to create something like a lie detector, except that it would look for signs of “paranoia” instead.

“Like a lie detector detects physical changes in the body based on sensitivities to specific questions, we believe there are physical changes in the body that are represented in observable behavioral changes when committing actions someone knows is wrong,” said the proposal. “Our solution is to develop a paranoia-meter to measure these observables.”

The idea was to take an HBGary rootkit like 12 Monkeys and install it on user machines in such a way that users could not remove it and might not even be aware of its presence. The rootkit would log user keystrokes, of course, but it would also take “as many behavioral measurements as possible” in order to look for suspicious activity that might indicate wrongdoing.

What sort of measurements? The rootkit would monitor “keystrokes, mouse movements, and visual cues through the system camera. We believe that during particularly risky activities we will see more erratic mouse movements and keystrokes as well as physical observations such as surveying surroundings, shifting more frequently, etc.”

But HBGary was also interested in applying its techniques for private clients as well:

But the e-mails also remind us how much of this work is carried out privately and beyond the control of government agencies. We found no evidence that HBGary sold malware to nongovernment entities intent on hacking, though the company did have plans to repurpose its DARPA rootkit idea for corporate surveillance work. (“HBGary plans to transition technology into commercial products,” it told DARPA.)

And another document, listing HBGary’s work over the last few years, included this entry: “HBGary had multiple contracts with a consumer software company to add stealth capability to their host agent.”

The actions of HBGary Federal’s Aaron Barr also serve as a good reminder that, when they’re searching for work, private security companies are more than happy to switch from military to corporate clients—and they bring some of the same tools to bear.

When asked to investigate pro-union websites and WikiLeaks, Barr turned immediately to his social media toolkit and was ready to deploy personas, Facebook scraping, link analysis, and fake websites; he also suggested computer attacks on WikiLeaks infrastructure and pressure be brought upon journalists like Glenn Greenwald.

His compatriots at Palantir and Berico showed, in their many e-mails, few if any qualms about turning their national security techniques upon private dissenting voices. Barr’s ideas showed up in Palantir-branded PowerPoints and Berico-branded “scope of work” documents. “Reconnaissance cells” were proposed, network attacks were acceptable, “target dossiers” on “adversaries” would be compiled, and “complex information campaigns” involving fake personas were on the table.

Ars Technica: Black ops: how HBGary wrote backdoors for the government

One of the more interesting proposals was for a “persona management” software for the Air Force. Raw Story has more details on this project. A mysterious company called Ntrepid eventually won that contract.

This isn’t the Air Force’s first foray into social media propaganda, it launched a blog commenting campaign in 2009.

February 23, 2011 0 comments