École Polytechnique Fédérale de Lausanne

About: École Polytechnique Fédérale de Lausanne is a facility organization based out in Lausanne, Switzerland. It is known for research contribution in the topics: Population & Catalysis. The organization has 44041 authors who have published 98296 publications receiving 4372092 citations. The organization is also known as: EPFL & ETHL.

X-Stream: edge-centric graph processing using streaming partitions

Abstract: X-Stream is a system for processing both in-memory and out-of-core graphs on a single shared-memory machine. While retaining the scatter-gather programming model with state stored in the vertices, X-Stream is novel in (i) using an edge-centric rather than a vertex-centric implementation of this model, and (ii) streaming completely unordered edge lists rather than performing random access. This design is motivated by the fact that sequential bandwidth for all storage media (main memory, SSD, and magnetic disk) is substantially larger than random access bandwidth.We demonstrate that a large number of graph algorithms can be expressed using the edge-centric scatter-gather model. The resulting implementations scale well in terms of number of cores, in terms of number of I/O devices, and across different storage media. X-Stream competes favorably with existing systems for graph processing. Besides sequential access, we identify as one of the main contributors to better performance the fact that X-Stream does not need to sort edge lists during preprocessing.

Stealing machine learning models via prediction APIs

Abstract: Machine learning (ML) models may be deemed confidential due to their sensitive training data, commercial value, or use in security applications. Increasingly often, confidential ML models are being deployed with publicly accessible query interfaces. ML-as-a-service ("predictive analytics") systems are an example: Some allow users to train models on potentially sensitive data and charge others for access on a pay-per-query basis. The tension between model confidentiality and public access motivates our investigation of model extraction attacks. In such attacks, an adversary with black-box access, but no prior knowledge of an ML model's parameters or training data, aims to duplicate the functionality of (i.e., "steal") the model. Unlike in classical learning theory settings, ML-as-a-service offerings may accept partial feature vectors as inputs and include confidence values with predictions. Given these practices, we show simple, efficient attacks that extract target ML models with near-perfect fidelity for popular model classes including logistic regression, neural networks, and decision trees. We demonstrate these attacks against the online services of BigML and Amazon Machine Learning. We further show that the natural countermeasure of omitting confidence values from model outputs still admits potentially harmful model extraction attacks. Our results highlight the need for careful ML model deployment and new model extraction countermeasures.

An optical-frequency synthesizer using integrated photonics

Abstract: Optical-frequency synthesizers, which generate frequency-stable light from a single microwave-frequency reference, are revolutionizing ultrafast science and metrology, but their size, power requirement and cost need to be reduced if they are to be more widely used. Integrated-photonics microchips can be used in high-coherence applications, such as data transmission1, highly optimized physical sensors2 and harnessing quantum states3, to lower cost and increase efficiency and portability. Here we describe a method for synthesizing the absolute frequency of a lightwave signal, using integrated photonics to create a phase-coherent microwave-to-optical link. We use a heterogeneously integrated III–V/silicon tunable laser, which is guided by nonlinear frequency combs fabricated on separate silicon chips and pumped by off-chip lasers. The laser frequency output of our optical-frequency synthesizer can be programmed by a microwave clock across 4 terahertz near 1,550 nanometres (the telecommunications C-band) with 1 hertz resolution. Our measurements verify that the output of the synthesizer is exceptionally stable across this region (synthesis error of 7.7 × 10−15 or below). Any application of an optical-frequency source could benefit from the high-precision optical synthesis presented here. Leveraging high-volume semiconductor processing built around advanced materials could allow such low-cost, low-power and compact integrated-photonics devices to be widely used. An optical-frequency synthesizer based on stabilized frequency combs has been developed utilizing chip-scale devices as key components, in a move towards using integrated photonics technology for ultrafast science and metrology.

The sixth visual object tracking VOT2018 challenge results

Abstract: The Visual Object Tracking challenge VOT2018 is the sixth annual tracker benchmarking activity organized by the VOT initiative. Results of over eighty trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years. The evaluation included the standard VOT and other popular methodologies for short-term tracking analysis and a “real-time” experiment simulating a situation where a tracker processes images as if provided by a continuously running sensor. A long-term tracking subchallenge has been introduced to the set of standard VOT sub-challenges. The new subchallenge focuses on long-term tracking properties, namely coping with target disappearance and reappearance. A new dataset has been compiled and a performance evaluation methodology that focuses on long-term tracking capabilities has been adopted. The VOT toolkit has been updated to support both standard short-term and the new long-term tracking subchallenges. Performance of the tested trackers typically by far exceeds standard baselines. The source code for most of the trackers is publicly available from the VOT page. The dataset, the evaluation kit and the results are publicly available at the challenge website (http://votchallenge.net).