The Center for Noise and Vibration Control at KAIST announced that their coughing detection camera recognizes where coughing happens, visualizing the locations. The resulting cough recognition camera can track and record information about the person who coughed, their location, and the number of coughs on a real-time basis.
CT-GAN: Malicious Tampering of 3D Medical Imagery using Deep Learning
In 2018, clinics and hospitals were hit with numerous attacks leading to significant data breaches and interruptions in medical services. An attacker with access to medical records can do much more than hold the data for ransom or sell it on the black market.
In this paper, we show how an attacker can use deep-learning to add or remove evidence of medical conditions from volumetric (3D) medical scans. An attacker may perform this act in order to stop a political candidate, sabotage research, commit insurance fraud, perform an act of terrorism, or even commit murder. We implement the attack using a 3D conditional GAN and show how the framework (CT-GAN) can be automated. Although the body is complex and 3D medical scans are very large, CT-GAN achieves realistic results which can be executed in milliseconds.
To evaluate the attack, we focused on injecting and removing lung cancer from CT scans. We show how three expert radiologists and a state-of-the-art deep learning AI are highly susceptible to the attack. We also explore the attack surface of a modern radiology network and demonstrate one attack vector: we intercepted and manipulated CT scans in an active hospital network with a covert penetration test.
In this paper, we present an automated learning environment for developing control policies directly on the hardware of a modular legged robot. This environment facilitates the reinforcement learning process by computing the rewards using a vision-based tracking system and relocating the robot to the initial position using a resetting mechanism. We employ two state-of-the-art deep reinforcement learning (DRL) algorithms, Trust Region Policy Optimization (TRPO) and Deep Deterministic Policy Gradient (DDPG), to train neural network policies for simple rowing and crawling motions. Using the developed environment, we demonstrate both learning algorithms can effectively learn policies for simple locomotion skills on highly stochastic hardware and environments. We further expedite learning by transferring policies learned on a single legged configuration to multi-legged ones.
Shared Autonomy via Deep Reinforcement Learning
Imagine a drone pilot remotely flying a quadrotor, using an onboard camera to navigate and land. Unfamiliar flight dynamics, terrain, and network latency can make this system challenging for a human to control. One approach to this problem is to train an autonomous agent to perform tasks like patrolling and mapping without human intervention. This strategy works well when the task is clearly specified and the agent can observe all the information it needs to succeed. Unfortunately, many real-world applications that involve human users do not satisfy these conditions: the user’s intent is often private information that the agent cannot directly access, and the task may be too complicated for the user to precisely define. For example, the pilot may want to track a set of moving objects (e.g., a herd of animals) and change object priorities on the fly (e.g., focus on individuals who unexpectedly appear injured). Shared autonomy addresses this problem by combining user input with automated assistance; in other words, augmenting human control instead of replacing it.
Deep Frog
do you think this is what lovecraft meant whenever he described something as being beyond description
“It was a terrible, indescribable thing vaster than any subway train—a shapeless congeries of protoplasmic bubbles, faintly self-luminous, and with myriads of temporary eyes forming and un-forming as pustules of greenish light all over the tunnel-filling front that bore down upon us, crushing the frantic penguins and slithering over the glistening floor that it and its kind had swept so evilly free of all litter.”
— H. P. Lovecraft,
At the Mountains of Madness
This.. actually makes a fine reference to what a lovecraftian eldritch abomination SHOULD BE. not just.. tentacles and darkness. Perpetually changing, not cemented in form, with an otherworldly feel to it. Completely unrecognizable by most human descriptions, and only able to be viable perceived by those fine enough to be an adept wordsmith.
I think that this is very nearly an ideal representation of a lovecraftian eldritch horror, because the video that we see is (I’m fairly certain) footage that has been fed through Google deep dream.
The reason the frog looks so weird is because the program is trying to look at the frog, figure out what it is, and then overlay other images of the same thing.
The the thing about lovecraftian horrors issn’t just that they look conventionally weird or gross or scary. Instead, they are things that are so utterly alien that the human mind cannot properly comprehend what it is looking at. They defy description because they defy understanding.
And here we have a video of a computer, a simple silicon substitute for the human mind, struggling to understand what it is looking at, in much the same way that you would be hard pressed to understand a shoggoth.
Traditionally, medical discoveries are made by observing associations, making hypotheses from them and then designing and running experiments to test the hypotheses. However, with medical images, observing and quantifying associations can often be difficult because of the wide variety of features, patterns, colours, values and shapes that are present in real data. Here, we show that deep learning can extract new knowledge from retinal fundus images. Using deep-learning models trained on data from 284,335 patients and validated on two independent datasets of 12,026 and 999 patients, we predicted cardiovascular risk factors not previously thought to be present or quantifiable in retinal images, such as age (mean absolute error within 3.26 years), gender (area under the receiver operating characteristic curve (AUC) = 0.97), smoking status (AUC = 0.71), systolic blood pressure (mean absolute error within 11.23 mmHg) and major adverse cardiac events (AUC = 0.70). We also show that the trained deep-learning models used anatomical features, such as the optic disc or blood vessels, to generate each prediction.
In this blog post, we’ll focus specifically on detection of RF signals modulated using Orthogonal Frequency Division Multiplexing (OFDM). OFDM is a digital multi-carrier modulation scheme that is employed in many fielded systems; WiFi, cable systems (e.g. DOCSIS 3.1) and cellular networks (e.g. 4G, 5G) either currently deploy or are moving towards OFDM as the PHY-layer standard. First, we will do a technical deep dive into OFDM to get a good understanding of the signal structure and it’s benefits. Next, we’ll introduce our patent pending signal detection system we’ve developed that uses deep learning (DL) to robustly detect OFDM waveforms by capturing only a portion of the total RF signal bandwidth.
In this article I’ll attempt to cover three things:
1. Two reasons why AlphaZero is a massive step forward for Artificial Intelligence
2. How you can build a replica of the AlphaZero methodology to play the game Connect4
3. How you can adapt the code to plug in other games
We present a method to create universal, robust, targeted adversarial image patches in the real world. The patches are universal because they can be used to attack any scene, robust because they work under a wide variety of transformations, and targeted because they can cause a classifier to output any target class. These adversarial patches can be printed, added to any scene, photographed, and presented to image classifiers; even when the patches are small, they cause the classifiers to ignore the other items in the scene and report a chosen target class.
Last month, a YouTube video of a conference talk in Berlin, shared widely among artificial-intelligence researchers, offered a possible answer. In the talk, Naftali Tishby, a computer scientist and neuroscientist from the Hebrew University of Jerusalem, presented evidence in support of a new theory explaining how deep learning works. Tishby argues that deep neural networks learn according to a procedure called the “information bottleneck,” which he and two collaborators first described in purely theoretical terms in 1999. The idea is that a network rids noisy input data of extraneous details as if by squeezing the information through a bottleneck, retaining only the features most relevant to general concepts. Striking new computer experiments by Tishby and his student Ravid Shwartz-Ziv reveal how this squeezing procedure happens during deep learning, at least in the cases they studied.
[…]
“The most important part of learning is actually forgetting.“
Malicious crowdsourcing forums are gaining traction as sources of spreading misinformation online, but are limited by the costs of hiring and managing human workers. In this paper, we identify a new class of attacks that leverage deep learning language models (Recurrent Neural Networks or RNNs) to automate the generation of fake online reviews for products and services. Not only are these attacks cheap and therefore more scalable, but they can control rate of content output to eliminate the signature burstiness that makes crowdsourced campaigns easy to detect.
Using Yelp reviews as an example platform, we show how a two phased review generation and customization attack can produce reviews that are indistinguishable by state-of-the-art statistical detectors. We conduct a survey-based user study to show these reviews not only evade human detection, but also score high on “usefulness” metrics by users. Finally, we develop novel automated defenses against these attacks, by leveraging the lossy transformation introduced by the RNN training and generation cycle. We consider countermeasures against our mechanisms, show that they produce unattractive cost-benefit tradeoffs for attackers, and that they can be further curtailed by simple constraints imposed by online service providers.
In drive tests performed inside MIT’s Stata Center, the robot, which resembles a knee-high kiosk on wheels, successfully avoided collisions while keeping up with the average flow of pedestrians. The researchers have detailed their robotic design in a paper that they will present at the IEEE Conference on Intelligent Robots and Systems in September.
It turns out LSTMs are a fairly simple extension to neural networks, and they’re behind a lot of the amazing achievements deep learning has made in the past few years. So I’ll try to present them as intuitively as possible – in such a way that you could have discovered them yourself.
kreuzaderny