Dark Reading is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them.Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

Vulnerabilities / Threats

1/21/2010
12:29 PM
50%
50%

Inside IBM's Patent Applications For Airport Security

Technology has potential to apply profiling of passengers, alerting officials to potential terminal and tarmac threats

A dozen little-known IBM patent applications lay out a sophisticated computer-analysis-based approach to airport security. The technology has the potential to apply profiling of passengers, based on attributes such as age and type of clothing worn. One of the patents IBM is seeking even appears to go Israeli-style security one better, using analysis of furtive glances in the application entitled "Detecting Behavioral Deviations By Measuring Eye Movements."

The objective of the technology in the passel of patent applications is to alert officials to potential terminal and tarmac threats using a network of video, motion, chemical, and biometric sensors arrayed throughout the airport. The sensors feed into a grid of networked computers, which provide high-powered processing to get results to officials in so-called real time, yet the systems are compact enough to be located on-site.

The "secret sauce" in the set up is a software "inference engine," which crunches the data fed in by the multitude of sensors, separating the high-risk wheat from the false-alarm chaff. That engine uses heuristics and rules developed by the three co-inventors behind the patent applications--Robert Angell, Robert Friedlander and James Kraemer.

"These patents are built on the inference engine, which has the ability to calculate very large data sets in real time," Angell told me last Friday.

He called me because he was surprised I had uncovered one of the patents, which I wrote about recently in my blog post, "Obama Security Push Spurring Scanner Patents (IBM's Seeking One)." That post focused on the patent application "Risk assessment in a pre/post security area within an airport."

Angell told me he believed the patents were under seal. That piqued my interest, because it indicated that this technology is probably more important -- in the sense of being proprietary and cutting edge -- than I had initially realized. As well, I knew of only the one patent and hadn't realized that, according to Angell, there were eight. (Since our conversation, I've uncovered 12 unique applications; the discrepancy might be due to the presence of duplicates--patent lawyers often revise and resubmit applications--or spin-offs.)

It turns out that, in fact, the patent applications are not under seal; that's something I don't think you can do, because the patent process is by definition open. Companies which want to shield proprietary technology go the trade-secret route, which means you keep your cutting-edge technology out of the public eye and hope no one will reverse-engineer it.

I have now tracked down all the applications, and will go into the technology details, below. [Update, Jan. 26: A paragraph in the original story stating that IBM didn't put down the company name as the assignee on three of its patent applications, which was based on failure to find that name on three applications viewed on the main patent search site, has been removed. The company name is present on the applications, when they've viewed via a different USPTO search. "We don't purposely withhold IBM's name from patent applications," as IBM spokesman said, and I accept that statement as fact.]

Angell also said that he's no longer with IBM. "I was laid off last year along with thousands of other people," he told me. Angell is currently teaching a computer science course at a community college in Salt Lake City, Utah, where he lives. I was flabbergasted, wondering how Big Blue could let go a guy like this, who obviously has heavy duty data-analysis chops and is behind such seemingly important technology.

Angell called me, he said, because he's concerned that the technology be applied effectively. "If it's done right, we could do passive profiling [and] passive detection and do it without a whole lot of fanfare," he said.

This profiling of potentially dangerous passengers, as outlined in the applications, appears in many ways to be more neutral than the profiling currently the subject of widespread public debate, because it's software-based and runs off of pre-programmed rules which, in general, are intended to identify suspicious behavior. (On the other hand, this wouldn't necessarily always apply, since markers such as a person's apparent age are listed in the patent applications as potential data points.)

Previous
1 of 3
Next
Comment  | 
Print  | 
More Insights
Comments
Newest First  |  Oldest First  |  Threaded View
vinayvinay
50%
50%
vinayvinay,
User Rank: Apprentice
8/5/2020 | 8:59:49 AM
Thanks for sharing valuable information
I am searching in google about some information related to patents, trademarks, here I came and found the information which I needed, Thanks for sharing valuable information.
COVID-19: Latest Security News & Commentary
Dark Reading Staff 9/25/2020
Hacking Yourself: Marie Moe and Pacemaker Security
Gary McGraw Ph.D., Co-founder Berryville Institute of Machine Learning,  9/21/2020
Startup Aims to Map and Track All the IT and Security Things
Kelly Jackson Higgins, Executive Editor at Dark Reading,  9/22/2020
Register for Dark Reading Newsletters
White Papers
Video
Cartoon
Current Issue
Special Report: Computing's New Normal
This special report examines how IT security organizations have adapted to the "new normal" of computing and what the long-term effects will be. Read it and get a unique set of perspectives on issues ranging from new threats & vulnerabilities as a result of remote working to how enterprise security strategy will be affected long term.
Flash Poll
How IT Security Organizations are Attacking the Cybersecurity Problem
How IT Security Organizations are Attacking the Cybersecurity Problem
The COVID-19 pandemic turned the world -- and enterprise computing -- on end. Here's a look at how cybersecurity teams are retrenching their defense strategies, rebuilding their teams, and selecting new technologies to stop the oncoming rise of online attacks.
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
CVE-2020-15208
PUBLISHED: 2020-09-25
In tensorflow-lite before versions 1.15.4, 2.0.3, 2.1.2, 2.2.1 and 2.3.1, when determining the common dimension size of two tensors, TFLite uses a `DCHECK` which is no-op outside of debug compilation modes. Since the function always returns the dimension of the first tensor, malicious attackers can ...
CVE-2020-15209
PUBLISHED: 2020-09-25
In tensorflow-lite before versions 1.15.4, 2.0.3, 2.1.2, 2.2.1 and 2.3.1, a crafted TFLite model can force a node to have as input a tensor backed by a `nullptr` buffer. This can be achieved by changing a buffer index in the flatbuffer serialization to convert a read-only tensor to a read-write one....
CVE-2020-15210
PUBLISHED: 2020-09-25
In tensorflow-lite before versions 1.15.4, 2.0.3, 2.1.2, 2.2.1 and 2.3.1, if a TFLite saved model uses the same tensor as both input and output of an operator, then, depending on the operator, we can observe a segmentation fault or just memory corruption. We have patched the issue in d58c96946b and ...
CVE-2020-15211
PUBLISHED: 2020-09-25
In TensorFlow Lite before versions 1.15.4, 2.0.3, 2.1.2, 2.2.1 and 2.3.1, saved models in the flatbuffer format use a double indexing scheme: a model has a set of subgraphs, each subgraph has a set of operators and each operator has a set of input/output tensors. The flatbuffer format uses indices f...
CVE-2020-15212
PUBLISHED: 2020-09-25
In TensorFlow Lite before versions 2.2.1 and 2.3.1, models using segment sum can trigger writes outside of bounds of heap allocated buffers by inserting negative elements in the segment ids tensor. Users having access to `segment_ids_data` can alter `output_index` and then write to outside of `outpu...