Artificial Demon Voice controls your Phone

Gepostet vor 5 Monaten, 28 Tagen in #Science #Tech #AI #AlgoCulture #Audio #Hacks

Share: Twitter Facebook Mail

Wissenschaftler haben eine Methode entwickelt, um Voice Commands in Sounds zu verstecken, die sich für das menschliche Ohr wie extrem und hundertfach komprimierte MP3s anhören. Mit diesen „Hidden Voice Commands“ können sie Android-Phones im Umkreis von bis zu drei Meter kontrollieren: The Demon Voice That Can Control Your Smartphone. (via Superpunch)

Voice interfaces are becoming more ubiquitous and are now the primary input method for many devices. We explore in this paper how they can be attacked with hidden voice commands that are unintelligible to human listeners but which are interpreted as commands by devices. We evaluate these attacks under two different threat models. In the black-box model, an attacker uses the speech recognition system as an opaque oracle. We show that the adversary can produce difficult to understand commands that are effective against existing systems in the black-box model. Under the white-box model, the attacker has full knowledge of the internals of the speech recognition system and uses it to create attack commands that we demonstrate through user testing are not understandable by humans. We then evaluate several defenses, including notifying the user when a voice command is accepted; a verbal challenge-response protocol; and a machine learning approach that can detect our attacks with 99.8% accuracy.

Sowas ähnliches gab's 2015 schon für Computer Vision, als sie Algorithmen erfolgreich mit Noise und Pattern verarscht hatten, Paper als PDF: Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images.

vis0

Deep neural networks (DNNs) have recently been achieving state-of-the-art performance on a variety of pattern-recognition tasks, most notably visual classification problems. Given that DNNs are now able to classify objects in images with near-human-level performance, questions naturally arise as to what differences remain between computer and human vision. A recent study [30] revealed that changing an image (e.g. of a lion) in a way imperceptible to humans can cause a DNN to label the image as something else entirely (e.g. mislabeling a lion a library).

Here we show a related result: it is easy to produce images that are completely unrecognizable to humans, but that state-of-theart DNNs believe to be recognizable objects with 99.99% confidence (e.g. labeling with certainty that white noise static is a lion). Specifically, we take convolutional neural networks trained to perform well on either the ImageNet or MNIST datasets and then find images with evolutionary algorithms or gradient ascent that DNNs label with high confidence as belonging to each dataset class. It is possible to produce images totally unrecognizable to human eyes that DNNs believe with near certainty are familiar objects, which we call “fooling images” (more generally, fooling examples). Our results shed light on interesting differences between human vision and current DNNs, and raise questions about the generality of DNN computer vision.

vis1 vis2 vis4 vis5

Cellular Automata Cube

Cubes.io: Conways Game of Life als 3D-Spielzeug mit Cubes und Spheres und Schnickschnack als Evolution-Nullpunkt, von wo aus die ganzen…

Neural Network-Faces synched to Music

„My first attempt to map a song made by @kamptweets onto GAN generated proto-faces.“ Bohemian Rhapsody next. The Three Nightingans.…

AI-Animations with human Sounds

Google vor ein paar Tagen so: „Yay, wir haben hier 'ne neue AI-based Animation-Tech, hooray!“ (Paper) Hayayo Miyazaki über AI-based…

Podcasts: Die Grenze des Sagbaren, Riot-Selfies, das Zeitalter des Zorns und der Summer of Love

Podcasts und Hörspiele, die ich in den letzten Wochen weggehört habe, unter anderem mit 'ner kurzen Kritik von Pankaj Mishras…

Visual AI-Spaces Auto-Pilot

Ich habe schon ein paar mal über Mario Klingemanns Arbeiten hier gebloggt, derzeit jagt er Neural Networks durch Feedback-Loops und…

Synthesizing Obama from Audio

Im Mai bloggte ich über ein damals noch nicht veröffentlichtes Paper zur SigGraph2017, in dem sie eine Methode für generative…

Generative Pearls

Cool fractal and generative art by Julien Leonard. I dig his explanation from his about-page: „I create algorithms that connect…

Moarph

Mario Klingemann does some weird shit again with CycleGAN Feedback Loops (Neural Networks feeding their results back to each other).…

Floral Algorithm dreams of Dinosaurs

Chris Rodley (Twitter) hat seinen Styletransfer-Bot mit Blumen gefüttert und auf Dinosaurier angesetzt.

3D-Visualized Typography-Ideaspace

Ich habe schon einige AI-Visualisierungen von Fonts gesehen, also sortierte Abbildungen des visuellen Idea-Space der Zeichensätze (also genau wie Skateboards…

Neural Network sorts Vibrators

Sabrina Verhage trainierte ein Neural Network auf Vibratoren und sortierte sie dann nach visuellen Merkmalen wie Farbe, Form, Pimmelrealismus und…