Tag Archives: self
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
The new Blade Runner sequel will return us to a world where sophisticated androids made with organic body parts can match the strength and emotions of their human creators. As someone who builds biologically inspired robots, I’m interested in whether our own technology will ever come close to matching the “replicants” of Blade Runner 2049.
The reality is that we’re a very long way from building robots with human-like abilities. But advances in so-called soft robotics show a promising way forward for technology that could be a new basis for the androids of the future.
From a scientific point of view, the real challenge is replicating the complexity of the human body. Each one of us is made up of millions and millions of cells, and we have no clue how we can build such a complex machine that is indistinguishable from us humans. The most complex machines today, for example the world’s largest airliner, the Airbus A380, are composed of millions of parts. But in order to match the complexity level of humans, we would need to scale this complexity up about a million times.
There are currently three different ways that engineering is making the border between humans and robots more ambiguous. Unfortunately, these approaches are only starting points and are not yet even close to the world of Blade Runner.
There are human-like robots built from scratch by assembling artificial sensors, motors, and computers to resemble the human body and motion. However, extending the current human-like robot would not bring Blade Runner-style androids closer to humans, because every artificial component, such as sensors and motors, are still hopelessly primitive compared to their biological counterparts.
There is also cyborg technology, where the human body is enhanced with machines such as robotic limbs and wearable and implantable devices. This technology is similarly very far away from matching our own body parts.
Finally, there is the technology of genetic manipulation, where an organism’s genetic code is altered to modify that organism’s body. Although we have been able to identify and manipulate individual genes, we still have a limited understanding of how an entire human emerges from genetic code. As such, we don’t know the degree to which we can actually program code to design everything we wish.
Soft robotics: a way forward?
But we might be able to move robotics closer to the world of Blade Runner by pursuing other technologies and, in particular, by turning to nature for inspiration. The field of soft robotics is a good example. In the last decade or so, robotics researchers have been making considerable efforts to make robots soft, deformable, squishable, and flexible.
This technology is inspired by the fact that 90% of the human body is made from soft substances such as skin, hair, and tissues. This is because most of the fundamental functions in our body rely on soft parts that can change shape, from the heart and lungs pumping fluid around our body to the eye lenses generating signals from their movement. Cells even change shape to trigger division, self-healing and, ultimately, the evolution of the body.
The softness of our bodies is the origin of all their functionality needed to stay alive. So being able to build soft machines would at least bring us a step closer to the robotic world of Blade Runner. Some of the recent technological advances include artificial hearts made out of soft functional materials that are pumping fluid through deformation. Similarly, soft, wearable gloves can help make hand grasping stronger. And “epidermal electronics” has enabled us to tattoo electronic circuits onto our biological skins.
Softness is the keyword that brings humans and technologies closer together. Sensors, motors, and computers are all of a sudden integrated into human bodies once they became soft, and the border between us and external devices becomes ambiguous, just like soft contact lenses became part of our eyes.
Nevertheless, the hardest challenge is how to make individual parts of a soft robot body physically adaptable by self-healing, growing, and differentiating. After all, every part of a living organism is also alive in biological systems in order to make our bodies totally adaptable and evolvable, the function of which could make machines totally indistinguishable from ourselves.
It is impossible to predict when the robotic world of Blade Runner might arrive, and if it does, it will probably be very far in the future. But as long as the desire to build machines indistinguishable from humans is there, the current trends of robotic revolution could make it possible to achieve that dream.
This article was originally published on The Conversation. Read the original article.
Image Credit: Dariush M / Shutterstock.com Continue reading
The brain has long inspired the design of computers and their software. Now Intel has become the latest tech company to decide that mimicking the brain’s hardware could be the next stage in the evolution of computing.
On Monday the company unveiled an experimental “neuromorphic” chip called Loihi. Neuromorphic chips are microprocessors whose architecture is configured to mimic the biological brain’s network of neurons and the connections between them called synapses.
While neural networks—the in vogue approach to artificial intelligence and machine learning—are also inspired by the brain and use layers of virtual neurons, they are still implemented on conventional silicon hardware such as CPUs and GPUs.
The main benefit of mimicking the architecture of the brain on a physical chip, say neuromorphic computing’s proponents, is energy efficiency—the human brain runs on roughly 20 watts. The “neurons” in neuromorphic chips carry out the role of both processor and memory which removes the need to shuttle data back and forth between separate units, which is how traditional chips work. Each neuron also only needs to be powered while it’s firing.
At present, most machine learning is done in data centers due to the massive energy and computing requirements. Creating chips that capture some of nature’s efficiency could allow AI to be run directly on devices like smartphones, cars, and robots.
This is exactly the kind of application Michael Mayberry, managing director of Intel’s research arm, touts in a blog post announcing Loihi. He talks about CCTV cameras that can run image recognition to identify missing persons or traffic lights that can track traffic flow to optimize timing and keep vehicles moving.
There’s still a long way to go before that happens though. According to Wired, so far Intel has only been working with prototypes, and the first full-size version of the chip won’t be built until November.
Once complete, it will feature 130,000 neurons and 130 million synaptic connections split between 128 computing cores. The device will be 1,000 times more energy-efficient than standard approaches, according to Mayberry, but more impressive are claims the chip will be capable of continuous learning.
Intel’s newly launched self-learning neuromorphic chip.
Normally deep learning works by training a neural network on giant datasets to create a model that can then be applied to new data. The Loihi chip will combine training and inference on the same chip, which will allow it to learn on the fly, constantly updating its models and adapting to changing circumstances without having to be deliberately re-trained.
A select group of universities and research institutions will be the first to get their hands on the new chip in the first half of 2018, but Mayberry said it could be years before it’s commercially available. Whether commercialization happens at all may largely depend on whether early adopters can get the hardware to solve any practically useful problems.
So far neuromorphic computing has struggled to gain traction outside the research community. IBM released a neuromorphic chip called TrueNorth in 2014, but the device has yet to showcase any commercially useful applications.
Lee Gomes summarizes the hurdles facing neuromorphic computing excellently in IEEE Spectrum. One is that deep learning can run on very simple, low-precision hardware that can be optimized to use very little power, which suggests complicated new architectures may struggle to find purchase.
It’s also not easy to transfer deep learning approaches developed on conventional chips over to neuromorphic hardware, and even Intel Labs chief scientist Narayan Srinivasa admitted to Forbes Loihi wouldn’t work well with some deep learning models.
Finally, there’s considerable competition in the quest to develop new computer architectures specialized for machine learning. GPU vendors Nvidia and AMD have pivoted to take advantage of this newfound market and companies like Google and Microsoft are developing their own in-house solutions.
Intel, for its part, isn’t putting all its eggs in one basket. Last year it bought two companies building chips for specialized machine learning—Movidius and Nervana—and this was followed up with the $15 billion purchase of self-driving car chip- and camera-maker Mobileye.
And while the jury is still out on neuromorphic computing, it makes sense for a company eager to position itself as the AI chipmaker of the future to have its fingers in as many pies as possible. There are a growing number of voices suggesting that despite its undoubted power, deep learning alone will not allow us to imbue machines with the kind of adaptable, general intelligence humans possess.
What new approaches will get us there are hard to predict, but it’s entirely possible they will only work on hardware that closely mimics the one device we already know is capable of supporting this kind of intelligence—the human brain.
Image Credit: Intel Continue reading
Robots perform many tasks that humans can't or don't want to perform, getting around on intricately designed wheels and limbs. If they tip over, however, they are rendered almost useless. A team of University of Illinois mechanical engineers and entomologists are looking to click beetles, who can right themselves without the use of their legs, to solve this robotics challenge. Continue reading