Biblio

Federated learning is a distributed learning technique where machine learning models are trained on client devices in which the local training data resides. The training is coordinated via a central server which is, typically, controlled by the intended owner of the resulting model. By avoiding the need to transport the training data to the central server, federated learning improves privacy and efficiency. But it raises the risk of model theft by clients because the resulting model is available on every client device. Even if the application software used for local training may attempt to prevent direct access to the model, a malicious client may bypass any such restrictions by reverse engineering the application software. Watermarking is a well-known deterrence method against model theft by providing the means for model owners to demonstrate ownership of their models. Several recent deep neural network (DNN) watermarking techniques use backdooring: training the models with additional mislabeled data. Backdooring requires full access to the training data and control of the training process. This is feasible when a single party trains the model in a centralized manner, but not in a federated learning setting where the training process and training data are distributed among several client devices. In this paper, we present WAFFLE, the first approach to watermark DNN models trained using federated learning. It introduces a retraining step at the server after each aggregation of local models into the global model. We show that WAFFLE efficiently embeds a resilient watermark into models incurring only negligible degradation in test accuracy (-0.17%), and does not require access to training data. We also introduce a novel technique to generate the backdoor used as a watermark. It outperforms prior techniques, imposing no communication, and low computational (+3.2%) overhead$^\textrm1$$^\textrm1$\$The research report version of this paper is also available in https://arxiv.org/abs/2008.07298, and the code for reproducing our work can be found at https://github.com/ssg-research/WAFFLE.

Machine learning (ML) applications are increasingly prevalent. Protecting the confidentiality of ML models becomes paramount for two reasons: (a) a model can be a business advantage to its owner, and (b) an adversary may use a stolen model to find transferable adversarial examples that can evade classification by the original model. Access to the model can be restricted to be only via well-defined prediction APIs. Nevertheless, prediction APIs still provide enough information to allow an adversary to mount model extraction attacks by sending repeated queries via the prediction API. In this paper, we describe new model extraction attacks using novel approaches for generating synthetic queries, and optimizing training hyperparameters. Our attacks outperform state-of-the-art model extraction in terms of transferability of both targeted and non-targeted adversarial examples (up to +29-44 percentage points, pp), and prediction accuracy (up to +46 pp) on two datasets. We provide take-aways on how to perform effective model extraction attacks. We then propose PRADA, the first step towards generic and effective detection of DNN model extraction attacks. It analyzes the distribution of consecutive API queries and raises an alarm when this distribution deviates from benign behavior. We show that PRADA can detect all prior model extraction attacks with no false positives.

Textual deception constitutes a major problem for online security. Many studies have argued that deceptiveness leaves traces in writing style, which could be detected using text classification techniques. By conducting an extensive literature review of existing empirical work, we demonstrate that while certain linguistic features have been indicative of deception in certain corpora, they fail to generalize across divergent semantic domains. We suggest that deceptiveness as such leaves no content-invariant stylistic trace, and textual similarity measures provide a superior means of classifying texts as potentially deceptive. Additionally, we discuss forms of deception beyond semantic content, focusing on hiding author identity by writing style obfuscation. Surveying the literature on both author identification and obfuscation techniques, we conclude that current style transformation methods fail to achieve reliable obfuscation while simultaneously ensuring semantic faithfulness to the original text. We propose that future work in style transformation should pay particular attention to disallowing semantically drastic changes.

Personal cryptographic keys are the foundation of many secure services, but storing these keys securely is a challenge, especially if they are used from multiple devices. Storing keys in a centralized location, like an Internet-accessible server, raises serious security concerns (e.g. server compromise). Hardware-based Trusted Execution Environments (TEEs) are a well-known solution for protecting sensitive data in untrusted environments, and are now becoming available on commodity server platforms. Although the idea of protecting keys using a server-side TEE is straight-forward, in this paper we validate this approach and show that it enables new desirable functionality. We describe the design, implementation, and evaluation of a TEE-based Cloud Key Store (CKS), an online service for securely generating, storing, and using personal cryptographic keys. Using remote attestation, users receive strong assurance about the behaviour of the CKS, and can authenticate themselves using passwords while avoiding typical risks of password-based authentication like password theft or phishing. In addition, this design allows users to i) define policy-based access controls for keys; ii) delegate keys to other CKS users for a specified time and/or a limited number of uses; and iii) audit all key usages via a secure audit log. We have implemented a proof of concept CKS using Intel SGX and integrated this into GnuPG on Linux and OpenKeychain on Android. Our CKS implementation performs approximately 6,000 signature operations per second on a single desktop PC. The latency is in the same order of magnitude as using locally-stored keys, and 20x faster than smart cards.

The theoretical construct of a Trusted Third Party (TTP) has the potential to solve many security and privacy challenges. In particular, a TTP is an ideal way to achieve secure multiparty computation—a privacy-enhancing technique in which mutually distrusting participants jointly compute a function over their private inputs without revealing these inputs. Although there exist cryptographic protocols to achieve this, their performance often limits them to the two-party case, or to a small number of participants. However, many real-world applications involve thousands or tens of thousands of participants. Examples of this type of many-party application include privacy-preserving energy metering, location-based services, and mobile network roaming. Challenging the notion that a trustworthy TTP does not exist, recent research has shown how trusted hardware and remote attestation can be used to establish a sufficient level of assurance in a real system such that it can serve as a trustworthy remote entity (TRE). We explore the use of Intel SGX, the most recent and arguably most promising trusted hardware technology, as the basis for a TRE for many-party applications. Using privacy-preserving energy metering as a case study, we design and implement a prototype TRE using SGX, and compare its performance to a previous system based on the Trusted Platform Module (TPM). Our results show that even without specialized optimizations, SGX provides comparable performance to the optimized TPM system, and therefore has significant potential for large-scale many-party applications.

Remote attestation is a crucial security service particularly relevant to increasingly popular IoT (and other embedded) devices. It allows a trusted party (verifier) to learn the state of a remote, and potentially malware-infected, device (prover). Most existing approaches are static in nature and only check whether benign software is initially loaded on the prover. However, they are vulnerable to runtime attacks that hijack the application's control or data flow, e.g., via return-oriented programming or data-oriented exploits. As a concrete step towards more comprehensive runtime remote attestation, we present the design and implementation of Control-FLow ATtestation (C-FLAT) that enables remote attestation of an application's control-flow path, without requiring the source code. We describe a full prototype implementation of C-FLAT on Raspberry Pi using its ARM TrustZone hardware security extensions. We evaluate C-FLAT's performance using a real-world embedded (cyber-physical) application, and demonstrate its efficacy against control-flow hijacking attacks.