Biblio

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 techniques 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" the model by retraining 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 defense. We conducted extensive, large-scale experiments using the ImageNet dataset, and show that our approaches eliminate up to 98% of gray-box attacks delivered by strong adversarial techniques such as Carlini-Wagner's L2 attack and DeepFool. Our approaches are fast and work without requiring knowledge about the model.

We introduce the fraud de-anonymization problem, that goes beyond fraud detection, to unmask the human masterminds responsible for posting search rank fraud in online systems. We collect and study search rank fraud data from Upwork, and survey the capabilities and behaviors of 58 search rank fraudsters recruited from 6 crowdsourcing sites. We propose Dolos, a fraud de-anonymization system that leverages traits and behaviors extracted from these studies, to attribute detected fraud to crowdsourcing site fraudsters, thus to real identities and bank accounts. We introduce MCDense, a min-cut dense component detection algorithm to uncover groups of user accounts controlled by different fraudsters, and leverage stylometry and deep learning to attribute them to crowdsourcing site profiles. Dolos correctly identified the owners of 95% of fraudster-controlled communities, and uncovered fraudsters who promoted as many as 97.5% of fraud apps we collected from Google Play. When evaluated on 13,087 apps (820,760 reviews), which we monitored over more than 6 months, Dolos identified 1,056 apps with suspicious reviewer groups. We report orthogonal evidence of their fraud, including fraud duplicates and fraud re-posts.

Cybersecurity analysts are often presented suspicious machine activity that does not conclusively indicate compromise, resulting in undetected incidents or costly investigations into the most appropriate remediation actions. There are many reasons for this: deficiencies in the number and quality of security products that are deployed, poor configuration of those security products, and incomplete reporting of product-security telemetry. Managed Security Service Providers (MSSP's), which are tasked with detecting security incidents on behalf of multiple customers, are confronted with these data quality issues, but also possess a wealth of cross-product security data that enables innovative solutions. We use MSSP data to develop Virtual Product, which addresses the aforementioned data challenges by predicting what security events would have been triggered by a security product if it had been present. This benefits the analysts by providing more context into existing security incidents (albeit probabilistic) and by making questionable security incidents more conclusive. We achieve up to 99% AUC in predicting the incidents that some products would have detected had they been present.

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.