Untrusted Machine Research Articles

Carbon: Scaling Trusted Payments with Untrusted Machines

Carbon: Scaling Trusted Payments with Untrusted Machines

CoFHE: Software and hardware Co-design for FHE-based machine learning as a service

Introduction: Privacy concerns arise whenever sensitive data is outsourced to untrusted Machine Learning as a Service (MLaaS) platforms. Fully Homomorphic Encryption (FHE) emerges one of the most promising solutions to implementing privacy-preserving MLaaS. But prior FHE-based MLaaS faces challenges from both software and hardware perspectives. First, FHE can be implemented by various schemes including BGV, BFV, and CKKS, which are good at different FHE operations, e.g., additions, multiplications, and rotations. Different neural network architectures require different numbers of FHE operations, thereby preferring different FHE schemes. However, state-of-the-art MLaaS just naïvely chooses one FHE scheme to build FHE-based neural networks without considering other FHE schemes. Second, state-of-the-art MLaaS uses power-hungry hardware accelerators to process FHE-based inferences. Typically, prior high-performance FHE accelerators consume >160 Watt, due to their huge capacity (e.g., 512 MB) on-chip SRAM scratchpad memories.Methods: In this paper, we propose a software and hardware co-designed FHE-based MLaaS framework, CoFHE. From the software perspective, we propose an FHE compiler to select the best FHE scheme for a network architecture. We also build a low-power and high-density NAND-SPIN and SRAM hybrid scratchpad memory system for FHE hardware accelerators.Results: On average, under the same security and accuracy constraints, on average, CoFHE accelerates various FHE-based inferences by 18%, and reduces the energy consumption of various FHE-based inferences by 26%.Discussion: CoFHE greatly improves the latency and energy efficiency of FHE-based MLaaS.

A video auditing system for display-based voting machines

The use of general-purpose computers as touch-screen voting machines has created several difficult auditing problems. If voting machines are compromised by malware, they can adapt their behavior to evade testing and auditing, and paper trails are achieved through printing devices under the untrusted machine’s control. In this paper we outline and exhibit a prototype of a device that audits a voting machine through screen capture, sampling the HDMI signal passed from the computer to the display. This is achieved through a standard that requires a compliant voting machine to display signal markers on the summary pages before a vote is cast; compliance is enforced via alerts to the voter with a visual and audible signal while the screen is captured and archived. This direct feedback to the voter prevents a compromised machine from failing to invoke the device. We discuss the design and prototype of this system and possible avenues for attack on it.

Defenses Against Byzantine Attacks in Distributed Deep Neural Networks

Large scale deep learning is trending recently, since people find that complicated networks can sometimes reach high accuracy on image recognition, natural language processing, etc. With the increasing complexity and batch size of deep neural networks, the training for such networks is more difficult because of the limited computational power and memory. Distributed machine learning or deep learning provides an efficient solution. However, with the concern of untrusted machines or hardware failures, the distributed system may suffer Byzantine attacks. If some workers are attacked and just upload malicious gradients to the parameter server, they will lead the total training process to a wrong model or even cannot converge. To defend the Byzantine attacks, we propose two efficient algorithms: FABA, a Fast Aggregation algorithm against Byzantine Attacks, and VBOR, a Variance Based Outlier Removal algorithm. FABA conducts the distance information to remove outliers one by one. VBOR uses the variance information to remove outliers with one-pass iteration. Theoretically, we prove the convergence of our algorithms and give an insight of the correctness. In the experiment, we compare FABA and VBOR with the state-of-the-art Byzantine defense algorithms and show our superior performance.

Local Differential Privacy for Deep Learning

The Internet of Things (IoT) is transforming major industries, including but not limited to healthcare, agriculture, finance, energy, and transportation. IoT platforms are continually improving with innovations, such as the amalgamation of software-defined networks (SDNs) and network function virtualization (NFV) in the edge-cloud interplay. Deep learning (DL) is becoming popular due to its remarkable accuracy when trained with a massive amount of data such as generated by IoT. However, DL algorithms tend to leak privacy when trained on highly sensitive crowd-sourced data such as medical data. The existing privacy-preserving DL algorithms rely on the traditional server-centric approaches requiring high processing powers. We propose a new local differentially private (LDP) algorithm named LATENT that redesigns the training process. LATENT enables a data owner to add a randomization layer before data leave the data owners' devices and reach a potentially untrusted machine learning service. This feature is achieved by splitting the architecture of a convolutional neural network (CNN) into three layers: 1) convolutional module (CNM); 2) randomization module; and 3) fully connected module. Hence, the randomization module can operate as an NFV privacy preservation service in an SDN-controlled NFV, making LATENT more practical for IoT-driven cloud-based environments compared to existing approaches. The randomization module employs a newly proposed LDP protocol named utility enhancing randomization, which allows LATENT to maintain high utility compared to existing LDP protocols. Our experimental evaluation of LATENT on convolutional deep neural networks demonstrates excellent accuracy (e.g., 91%-96%) with high model quality even under low privacy budgets (e.g., ε = 0.5).

Battering Keyloggers and Screen Recording Software by Fabricating Passwords

6 Abstract — The keyloggers are covert security threat to the privacy and identity of users. The attackers are exploring different techniques of keylogging using hardware keyloggers, software keyloggers and screen capturing software to steal the user sensitive data. The Incognizance of the user is imposing greater risk. To overcome this problem, we have proposed a model. In this model solution to Keylogger and Screen Recording Software has been proposed by using the concept of fabricated password on untrusted machine. It deceives the untrusted system's key logging and video capturing software. The concept used here is WYSINT What You See Is Not True. The main feature of this model is that it has a hardware recognition to retrieve the key .This key is required by the Temporary Filter layer (TFL) as an intermediary to change into the trusted password after bypassing all the capturing techniques and returning the original password to the required website.

A snapshot of trusted personal devices applicable to transaction processing

In recent years, a clear trend has emerged where businesses need to provide flexible access to its services so as to increase their usage by a much wider cross-section of users operating over public infrastructures but still within a trusted environment. This trusted environment must be established between all participating users and service provider entities before any transactions are carried out. To meet the challenge of enabling mobile users to work within a trusted environment on any untrusted machine, the notion of a trusted personal device (TPD) has emerged. This paper provides a survey giving a snapshot of the growing body of work ongoing in the area of TPDs and the services they support.

Secure audit logs to support computer forensics

In many real-world applications, sensitive information must be kept it log files on an untrusted machine. In the event that an attacker captures this machine, we would like to guarantee that he will gain little or no information from the log files and to limit his ability to corrupt the log files. We describe a computationally cheap method for making all log entries generated prior to the logging machine's compromise impossible for the attacker to read, and also impossible to modify or destroy undetectably.