arXiv subjects

Duen Horng Chau

Publications and source records attributed to Duen Horng Chau.

121 records · Page 7Linked to original sources

arXiv2018

Shield: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compression

The rapidly growing body of research in adversarial machine learning has demonstrated that deep neural networks (DNNs) are highly vulnerable to adversarially generated images. This underscores the urgent need for practical defense that can be readily deployed to combat attacks in real-time. Observing that many attack strategies aim to perturb image pixels in ways that are visually imperceptible, we place JPEG compression at the core of our proposed Shield defense framework, utilizing its capability to effectively "compress away" such pixel manipulation. To immunize a DNN model from artifacts introduced by compression, Shield "vaccinates" a model by re-training it with compressed images, where different compression levels are applied to generate multiple vaccinated models that are ultimately used together in an ensemble defense. On top of that, Shield adds an additional layer of protection by employing randomization at test time that compresses different regions of an image using random compression levels, making it harder for an adversary to estimate the transformation performed. This novel combination of vaccination, ensembling, and randomization makes Shield a fortified multi-pronged protection. We conducted extensive, large-scale experiments using the ImageNet dataset, and show that our approaches eliminate up to 94% of black-box attacks and 98% of gray-box attacks delivered by the recent, strongest attacks, such as Carlini-Wagner's L2 and DeepFool. Our approaches are fast and work without requiring knowledge about the model.

cs.CV↗

arXiv2017

ActiVis: Visual Exploration of Industry-Scale Deep Neural Network Models

While deep learning models have achieved state-of-the-art accuracies for many prediction tasks, understanding these models remains a challenge. Despite the recent interest in developing visual tools to help users interpret deep learning models, the complexity and wide variety of models deployed in industry, and the large-scale datasets that they used, pose unique design challenges that are inadequately addressed by existing work. Through participatory design sessions with over 15 researchers and engineers at Facebook, we have developed, deployed, and iteratively improved ActiVis, an interactive visualization system for interpreting large-scale deep learning models and results. By tightly integrating multiple coordinated views, such as a computation graph overview of the model architecture, and a neuron activation view for pattern discovery and comparison, users can explore complex deep neural network models at both the instance- and subset-level. ActiVis has been deployed on Facebook's machine learning platform. We present case studies with Facebook researchers and engineers, and usage scenarios of how ActiVis may work with different models.

cs.HC↗

arXiv2017

Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compression

Deep neural networks (DNNs) have achieved great success in solving a variety of machine learning (ML) problems, especially in the domain of image recognition. However, recent research showed that DNNs can be highly vulnerable to adversarially generated instances, which look seemingly normal to human observers, but completely confuse DNNs. These adversarial samples are crafted by adding small perturbations to normal, benign images. Such perturbations, while imperceptible to the human eye, are picked up by DNNs and cause them to misclassify the manipulated instances with high confidence. In this work, we explore and demonstrate how systematic JPEG compression can work as an effective pre-processing step in the classification pipeline to counter adversarial attacks and dramatically reduce their effects (e.g., Fast Gradient Sign Method, DeepFool). An important component of JPEG compression is its ability to remove high frequency signal components, inside square blocks of an image. Such an operation is equivalent to selective blurring of the image, helping remove additive perturbations. Further, we propose an ensemble-based technique that can be constructed quickly from a given well-performing DNN, and empirically show how such an ensemble that leverages JPEG compression can protect a model from multiple types of adversarial attacks, without requiring knowledge about the model.

cs.CV↗

arXiv2017

FairPlay: Fraud and Malware Detection in Google Play

Fraudulent behaviors in Google Android app market fuel search rank abuse and malware proliferation. We present FairPlay, a novel system that uncovers both malware and search rank fraud apps, by picking out trails that fraudsters leave behind. To identify suspicious apps, FairPlay PCF algorithm correlates review activities and uniquely combines detected review relations with linguistic and behavioral signals gleaned from longitudinal Google Play app data. We contribute a new longitudinal app dataset to the community, which consists of over 87K apps, 2.9M reviews, and 2.4M reviewers, collected over half a year. FairPlay achieves over 95% accuracy in classifying gold standard datasets of malware, fraudulent and legitimate apps. We show that 75% of the identified malware apps engage in search rank fraud. FairPlay discovers hundreds of fraudulent apps that currently evade Google Bouncer detection technology, and reveals a new type of attack campaign, where users are harassed into writing positive reviews, and install and review other apps.

cs.SI↗

arXiv2017

Carina: Interactive Million-Node Graph Visualization using Web Browser Technologies

We are working on a scalable, interactive visualization system, called Carina, for people to explore million-node graphs. By using latest web browser technologies, Carina offers fast graph rendering via WebGL, and works across desktop (via Electron) and mobile platforms. Different from most existing graph visualization tools, Carina does not store the full graph in RAM, enabling it to work with graphs with up to 69M edges. We are working to improve and open-source Carina, to offer researchers and practitioners a new, scalable way to explore and visualize large graph datasets.

cs.HC↗

arXiv2017

Scalable Architecture for Anomaly Detection and Visualization in Power Generating Assets

Power-generating assets (e.g., jet engines, gas turbines) are often instrumented with tens to hundreds of sensors for monitoring physical and performance degradation. Anomaly detection algorithms highlight deviations from predetermined benchmarks with the goal of detecting incipient faults. We are developing an integrated system to address three key challenges within analyzing sensor data from power-generating assets: (1) difficulty in ingesting and analyzing data from large numbers of machines; (2) prevalence of false alarms generated by anomaly detection algorithms resulting in unnecessary downtime and maintenance; and (3) lack of an integrated visualization that helps users understand and explore the flagged anomalies and relevant sensor context in the energy domain. We present preliminary results and our key findings in addressing these challenges. Our system's scalable event ingestion framework, based on OpenTSDB, ingests nearly 400,000 sensor data samples per seconds using a 30 machine cluster. To reduce false alarm rates, we leverage the False Discovery Rate (FDR) algorithm which significantly reduces the number of false alarms. Our visualization tool presents the anomalies and associated content flagged by the FDR algorithm to inform users and practitioners in their decision making process. We believe our integrated platform will help reduce maintenance costs significantly while increasing asset lifespan. We are working to extend our system on multiple fronts, such as scaling to more data and more compute nodes (70 in total).

cs.DC↗

arXiv2016

Communication Efficient Distributed Agnostic Boosting

We consider the problem of learning from distributed data in the agnostic setting, i.e., in the presence of arbitrary forms of noise. Our main contribution is a general distributed boosting-based procedure for learning an arbitrary concept space, that is simultaneously noise tolerant, communication efficient, and computationally efficient. This improves significantly over prior works that were either communication efficient only in noise-free scenarios or computationally prohibitive. Empirical results on large synthetic and real-world datasets demonstrate the effectiveness and scalability of the proposed approach.

cs.LG↗

arXiv2016

Chronodes: Interactive Multi-focus Exploration of Event Sequences

The advent of mobile health technologies presents new challenges that existing visualizations, interactive tools, and algorithms are not yet designed to support. In dealing with uncertainty in sensor data and high-dimensional physiological records, we must seek to improve current tools that make sense of health data from traditional perspectives in event-based trend discovery. With Chronodes, a system developed to help researchers collect, interpret, and model mobile health (mHealth) data, we posit a series of interaction techniques that enable new approaches to understanding and exploring event-based data. From numerous and discontinuous mobile health data streams, Chronodes finds and visualizes frequent event sequences that reveal common chronological patterns across participants and days. By then promoting the sequences as interactive elements, Chronodes presents opportunities for finding, defining, and comparing cohorts of participants that exhibit particular behaviors. We applied Chronodes to a real 40GB mHealth dataset capturing about 400 hours of data. Through our pilot study with 20 behavioral and biomedical health experts, we gained insights into Chronodes' efficacy, limitations, and potential applicability to a wide range of healthcare scenarios.

cs.HC↗

arXiv2016

Interactive Browsing and Navigation in Relational Databases

Although researchers have devoted considerable attention to helping database users formulate queries, many users still find it challenging to specify queries that involve joining tables. To help users construct join queries for exploring relational databases, we propose ETable, a novel presentation data model that provides users with a presentation-level interactive view. This view compactly presents one-to-many and many-to-many relationships within a single enriched table by allowing a cell to contain a set of entity references. Users can directly interact with this enriched table to incrementally construct complex queries and navigate databases on a conceptual entity-relationship level. In a user study, participants performed a range of database querying tasks faster with ETable than with a commercial graphical query builder. Subjective feedback about ETable was also positive. All participants found that ETable was easier to learn and helpful for exploring databases.

cs.DB↗

arXiv2016

Seeing the Forest through the Trees: Adaptive Local Exploration of Large Graphs

Visualization is a powerful paradigm for exploratory data analysis. Visualizing large graphs, however, often results in a meaningless hairball. In this paper, we propose a different approach that helps the user adaptively explore large million-node graphs from a local perspective. For nodes that the user investigates, we propose to only show the neighbors with the most subjectively interesting neighborhoods. We contribute novel ideas to measure this interestingness in terms of how surprising a neighborhood is given the background distribution, as well as how well it fits the nodes the user chose to explore. We introduce FACETS, a fast and scalable method for visually exploring large graphs. By implementing our above ideas, it allows users to look into the forest through its trees. Empirical evaluation shows that our method works very well in practice, providing rankings of nodes that match interests of users. Moreover, as it scales linearly, FACETS is suited for the exploration of very large graphs.

cs.IR↗

arXiv2016

Firebird: Predicting Fire Risk and Prioritizing Fire Inspections in Atlanta

The Atlanta Fire Rescue Department (AFRD), like many municipal fire departments, actively works to reduce fire risk by inspecting commercial properties for potential hazards and fire code violations. However, AFRD's fire inspection practices relied on tradition and intuition, with no existing data-driven process for prioritizing fire inspections or identifying new properties requiring inspection. In collaboration with AFRD, we developed the Firebird framework to help municipal fire departments identify and prioritize commercial property fire inspections, using machine learning, geocoding, and information visualization. Firebird computes fire risk scores for over 5,000 buildings in the city, with true positive rates of up to 71% in predicting fires. It has identified 6,096 new potential commercial properties to inspect, based on AFRD's criteria for inspection. Furthermore, through an interactive map, Firebird integrates and visualizes fire incidents, property information and risk scores to help AFRD make informed decisions about fire inspections. Firebird has already begun to make positive impact at both local and national levels. It is improving AFRD's inspection processes and Atlanta residents' safety, and was highlighted by National Fire Protection Association (NFPA) as a best practice for using data to inform fire inspections.

cs.CY↗

arXiv2016

GraphPrints: Towards a Graph Analytic Method for Network Anomaly Detection

This paper introduces a novel graph-analytic approach for detecting anomalies in network flow data called GraphPrints. Building on foundational network-mining techniques, our method represents time slices of traffic as a graph, then counts graphlets -- small induced subgraphs that describe local topology. By performing outlier detection on the sequence of graphlet counts, anomalous intervals of traffic are identified, and furthermore, individual IPs experiencing abnormal behavior are singled-out. Initial testing of GraphPrints is performed on real network data with an implanted anomaly. Evaluation shows false positive rates bounded by 2.84% at the time-interval level, and 0.05% at the IP-level with 100% true positive rates at both.

cs.CR↗

arXiv2015

Spotting Suspicious Reviews via (Quasi-)clique Extraction

How to tell if a review is real or fake? What does the underworld of fraudulent reviewing look like? Detecting suspicious reviews has become a major issue for many online services. We propose the use of a clique-finding approach to discover well-organized suspicious reviewers. From a Yelp dataset with over one million reviews, we construct multiple Reviewer Similarity graphs to link users that have unusually similar behavior: two reviewers are connected in the graph if they have reviewed the same set of venues within a few days. From these graphs, our algorithms extracted many large cliques and quasi-cliques, the largest one containing a striking 11 users who coordinated their review activities in identical ways. Among the detected cliques, a large portion contain Yelp Scouts who are paid by Yelp to review venues in new areas. Our work sheds light on their little-known operation.

cs.SI↗