Tag Archives: introducing
Con artistry is one of the world’s oldest and most innovative professions, and it may soon have a new target. Research suggests artificial intelligence may be uniquely susceptible to tricksters, and as its influence in the modern world grows, attacks against it are likely to become more common.
The root of the problem lies in the fact that artificial intelligence algorithms learn about the world in very different ways than people do, and so slight tweaks to the data fed into these algorithms can throw them off completely while remaining imperceptible to humans.
Much of the research into this area has been conducted on image recognition systems, in particular those relying on deep learning neural networks. These systems are trained by showing them thousands of examples of images of a particular object until they can extract common features that allow them to accurately spot the object in new images.
But the features they extract are not necessarily the same high-level features a human would be looking for, like the word STOP on a sign or a tail on a dog. These systems analyze images at the individual pixel level to detect patterns shared between examples. These patterns can be obscure combinations of pixel values, in small pockets or spread across the image, that would be impossible to discern for a human, but highly accurate at predicting a particular object.
“An attacker can trick the object recognition algorithm into seeing something that isn’t there, without these alterations being obvious to a human.”
What this means is that by identifying these patterns and overlaying them over a different image, an attacker can trick the object recognition algorithm into seeing something that isn’t there, without these alterations being obvious to a human. This kind of manipulation is known as an “adversarial attack.”
Early attempts to trick image recognition systems this way required access to the algorithm’s inner workings to decipher these patterns. But in 2016 researchers demonstrated a “black box” attack that enabled them to trick such a system without knowing its inner workings.
By feeding the system doctored images and seeing how it classified them, they were able to work out what it was focusing on and therefore generate images they knew would fool it. Importantly, the doctored images were not obviously different to human eyes.
These approaches were tested by feeding doctored image data directly into the algorithm, but more recently, similar approaches have been applied in the real world. Last year it was shown that printouts of doctored images that were then photographed on a smartphone successfully tricked an image classification system.
Another group showed that wearing specially designed, psychedelically-colored spectacles could trick a facial recognition system into thinking people were celebrities. In August scientists showed that adding stickers to stop signs in particular configurations could cause a neural net designed to spot them to misclassify the signs.
These last two examples highlight some of the potential nefarious applications for this technology. Getting a self-driving car to miss a stop sign could cause an accident, either for insurance fraud or to do someone harm. If facial recognition becomes increasingly popular for biometric security applications, being able to pose as someone else could be very useful to a con artist.
Unsurprisingly, there are already efforts to counteract the threat of adversarial attacks. In particular, it has been shown that deep neural networks can be trained to detect adversarial images. One study from the Bosch Center for AI demonstrated such a detector, an adversarial attack that fools the detector, and a training regime for the detector that nullifies the attack, hinting at the kind of arms race we are likely to see in the future.
While image recognition systems provide an easy-to-visualize demonstration, they’re not the only machine learning systems at risk. The techniques used to perturb pixel data can be applied to other kinds of data too.
“Bypassing cybersecurity defenses is one of the more worrying and probable near-term applications for this approach.”
Chinese researchers showed that adding specific words to a sentence or misspelling a word can completely throw off machine learning systems designed to analyze what a passage of text is about. Another group demonstrated that garbled sounds played over speakers could make a smartphone running the Google Now voice command system visit a particular web address, which could be used to download malware.
This last example points toward one of the more worrying and probable near-term applications for this approach: bypassing cybersecurity defenses. The industry is increasingly using machine learning and data analytics to identify malware and detect intrusions, but these systems are also highly susceptible to trickery.
At this summer’s DEF CON hacking convention, a security firm demonstrated they could bypass anti-malware AI using a similar approach to the earlier black box attack on the image classifier, but super-powered with an AI of their own.
Their system fed malicious code to the antivirus software and then noted the score it was given. It then used genetic algorithms to iteratively tweak the code until it was able to bypass the defenses while maintaining its function.
All the approaches noted so far are focused on tricking pre-trained machine learning systems, but another approach of major concern to the cybersecurity industry is that of “data poisoning.” This is the idea that introducing false data into a machine learning system’s training set will cause it to start misclassifying things.
This could be particularly challenging for things like anti-malware systems that are constantly being updated to take into account new viruses. A related approach bombards systems with data designed to generate false positives so the defenders recalibrate their systems in a way that then allows the attackers to sneak in.
How likely it is that these approaches will be used in the wild will depend on the potential reward and the sophistication of the attackers. Most of the techniques described above require high levels of domain expertise, but it’s becoming ever easier to access training materials and tools for machine learning.
Simpler versions of machine learning have been at the heart of email spam filters for years, and spammers have developed a host of innovative workarounds to circumvent them. As machine learning and AI increasingly embed themselves in our lives, the rewards for learning how to trick them will likely outweigh the costs.
Image Credit: Nejron Photo / Shutterstock.com Continue reading
Tech-Link Healthcare Systems partners with Blue Ocean Robotics Introducing UV-Disinfection Robot
Singapore, 1 November 2016 – The rise of robots have steered Tech-Link Healthcare Systems, a design and integrator of healthcare automation systems to offer solutions beyond automated storage and material handling systems. With a vision of providing holistic solutions for healthcare organisations, Tech-Link extends its capabilities by offering UV disinfection robot solutions via a strategic partnership with Danish robotics company, Blue Ocean Robotics to battle against Hospital Acquired Infections (HAIs).Singapore’s labour intensive healthcare environment and the unknown impact of HAIs in the developed city-state had beckoned Tech-Link Healthcare Systems to offer solutions in the area of disinfection. We recognised the rise in demand for robots to collaborate with humans and have identified this need for customers. Introducing robotic technologies as part of our suite of solutions is the company’s mission to innovate the way healthcare organisations work and enhance their customers’ experience.Tech-Link’s partnership with Blue Ocean Robotics affirms both companies’ efforts in reaching out to new markets with technology and solutions to ease manpower crunch, deliver greater value and improve the quality of healthcare services. As an official sales partner, we bring together Blue Ocean Robotics’ expertise in automating disinfection procedures to promote safer, efficient and more productive work environment.
“Tech-Link looks forward to developing reliable healthcare solutions with hardware and latest technologies from Blue Ocean Robotics for our customers in Singapore and abroad.” said Director of Tech-Link Healthcare Systems, Tan Hock Seng. “Our similar beliefs in the Blue Ocean strategy synergise the collaboration to improve the quality of healthcare services through robotics.” he added.“We are very excited about our new sales partner Tech-Link Healthcare Systems, since it is of great importance for Blue Ocean Robotics to expand our sales of new technologies beyond Denmark’s borders. Blue Ocean Robotics focuses on creating new markets for robots. This includes both the development of new technologies and the creation of new markets for revolutionary robot solutions. We welcome Tech-Link Healthcare Systems with open arms and look forward to a fruitful collaboration in the years ahead.” said Claus Risager, Rune K. Larsen & John Erland Østergaard, Partners and Co-CEOs, Blue Ocean Robotics.
UV-Disinfection RobotThe UV-Disinfection Robot – also called UV-DR – is an autonomous disinfection robot for hospitals, production lines and pharmaceutical companies. The robot is used primarily in, but not limited to the cleaning cycle with the aim of reducing spread of HAIs, infectious diseases, viruses, bacteria and other types or harmful organic materials.UV-DR is a mobile robot that can drive autonomously while emitting concentrated UV-C light onto pre-defined infectious hotspots in patient rooms and other hospital environments, thus disinfecting and killing bacteria and virus on all exposed surfaces. An exposure time of ten minutes is estimated to kill up to 99% of bacteria such as Clostridium Difficile.
About Tech-Link Healthcare Systems Pte LtdTech-Link Healthcare Systems is a subsidiary of Tech-Link Storage Engineering established in Singapore since 2015. The company designs and provides innovative solutions for the healthcare sector, focusing on advanced and emerging solutions to support healthcare organisations in optimising available resources and services. Tech-Link Healthcare Systems design and implement automated material handling systems to enhance secured material transport and logistics storage management in hospitals and other healthcare facilities. As a complete solution provider, the company also provides consultancy in systems design to streamline and automate processes as well as integrated video solutions within healthcare facilities.About Tech-Link Storage Engineering Pte LtdTech-Link Storage Engineering is a group of companies established in Singapore with more than 25 years of principal activities in procurement, manufacturing and marketing of storage, distribution and materials handling products and systems. From its domain expertise in storage and racking systems, Tech-Link is also involved in R&D, system design, supply and implementation of logistics supply chain automation systems. The business expanded its global capabilities in the area of planning and consultancy to provide solutions for Built-to-Suit industrial developments and Healthcare logistics systems.
Tech-Link is an ISO 9001:2008 and OHSAS 18001:2007 certified company for Quality Management System and Occupational, Health and Safety System.Visit www.techlinkstorageengineering.comAbout Blue Ocean RoboticsBlue Ocean Robotics is an international company group with presence across the globe including America, Europe, Asia and Australia. The robotics company has its headquarter in the city of Odense (www.odenserobotics.dk) in Denmark. Blue Ocean Robotics applies robot technology to create solutions and innovation for end-users and new businesses in partnerships.Visit www.blue-ocean-robotics.com
Here is a video showing the robot in action:
The post UV Disinfection robot appeared first on Roboticmagazine. Continue reading