Counterfeiting of physical goods is a global problem amounting to nearly 7% of world trade. While there have been a variety of overt technologies like holograms and specialized barcodes and covert technologies like taggants and PUFs, these solutions have had a limited impact on the counterfeit market due to a variety of factors - clonability, cost or adoption barriers. In this paper, we introduce a new mechanism that uses machine learning algorithms on microscopic images of physical objects to distinguish between genuine and counterfeit versions of the same product. The underlying principle of our system stems from the idea that microscopic characteristics in a genuine product or a class of products (corresponding to the same larger product line), exhibit inherent similarities that can be used to distinguish these products from their corresponding counterfeit versions. A key building block for our system is a wide-angle microscopy device compatible with a mobile device that enables a user to easily capture the microscopic image of a large area of a physical object. Based on the captured microscopic images, we show that using machine learning algorithms (ConvNets and bag of words), one can generate a highly accurate classification engine for separating the genuine versions of a product from the counterfeit ones; this property also holds for "super-fake" counterfeits observed in the marketplace that are not easily discernible from the human eye. We describe the design of an end-to-end physical authentication system leveraging mobile devices, portable hardware and a cloud-based object verification ecosystem. We evaluate our system using a large dataset of 3 million images across various objects and materials such as fabrics, leather, pills, electronics, toys and shoes. The classification accuracy is more than 98% and we show how our system works with a cellphone to verify the authenticity of everyday objects.

Paper forgery is among the leading causes of corruption in many developing regions. In this paper, we introduce PaperSpeckle, a robust system that leverages the natural randomness property present in paper to generate a fingerprint for any piece of paper. Our goal in developing PaperSpeckle is to build a low-cost paper based authentication mechanism for applications in rural regions such as microfinance, healthcare, land ownership records, supply chain services and education which heavily rely on paper based records. Unlike prior paper fingerprinting techniques that have extracted fingerprints based on the fiber structure of paper, PaperSpeckle uses the texture speckle pattern, a random bright/dark region formation at the microscopic level when light falls on to the paper, to extract a unique fingerprint to identify paper. In PaperSpeckle, we show how to extract a "repeatable" texture speckle pattern of a microscopic region of a paper using low-cost machinery involving paper, pen and a cheap microscope. Using extensive testing on different types of paper, we show that PaperSpeckle can produce a robust repeatable fingerprint even if paper is damaged due to crumpling, printing or scribbling, soaking in water or aging with time.

While the cellular revolution has made voice connectivity ubiquitous in the developing world, data services are largely absent or are prohibitively expensive. In this paper, we present Hermes1, a point-to-point data connectivity solution that works by modulating data onto acoustic signals that are sent over a cellular voice call. The main challenge is that most voice codecs greatly distort signals that are not voice-like; furthermore, the backhaul can be highly heterogeneous and of low quality, thereby introducing unpredictable distortions. Hermes modulates data over the extremely narrow-band approximately 3kHz bandwidth) acoustic carrier, while being severely constrained by the requirement that the resulting sound signals are voice-like, as far as the voice codecs are concerned. Hermes uses a robust data transcoding and modulation scheme to detect and correct errors in the face of bit flips, insertions and deletions; it also adapts the modulation parameters to the observed bit error rate on the actual voice channel. Through real-world experiments, we show that Hermes achieves approximately 1.2 kbps goodput which when compared to SMS, improves throughput by a factor of 5× and reduces the cost-per-byte by over a factor of 50x

Nearly 40 million people in Africa suffer from HIV/AIDS. African governments and international aid agencies have been working to combat this epidemic by vigorously promoting Highly Active Anti-Retroviral Therapy (HAART) programs. Despite the enormous subsidies offered by governments along with free Anti-RetroViral (ARV) drugs supplied by agencies, the introduction and implementation of HAART programs on a large scale has been limited by two fundamental problems: (a) lack of adherence to the ARV therapy regimen; (b) lack of accountability in drug distribution due to theft, corruption and counterfeit medication. In this paper, we motivate the case for SmartTrack, a telehealth project which aims to address these two problems facing HAART programs. The goal of SmartTrack is to create a highly reliable, secure and ultra low-cost cellphone-based distributed drug information system that can be used for tracking the flow and consumption of ARV drugs in HAART programs. In this paper, we assess the potential benefit of SmartTrack using a detailed needs-assessment study performed in Ghana, using interviews with 516 HIV-positive rural patients in a number of locations across the country. We find that a system like SmartTrack would immensely benefit both patients and healthcare providers, and can ultimately lead to improved patient outcomes and better accountability.