Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userA CRISPR-Cas-Inspired Mechanism for Detecting Hardware Trojans in FPGA Devices
53
0
0.0
(
0
)
Added by
Dillon Staub
Publication date
2020
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Hardware security has risen in prominence in recent years with concerns stemming from a globalizing semiconductor supply chain and increased third-party IP (intellectual property) usage. Trojan detection is of paramount importance for ensuring systems with confidentiality, integrity, and availability. Existing methods for hardware Trojan detection in FPGA (field programmable gate array) devices include test-time methods, pre-implementation methods, and run-time methods. The first two methods provide effective ways of detecting some Trojans; however, Trojans may be specifically designed to avoid detection at test-time or before implementation making run-time detection a more attractive option. Run-time detection and removal of Trojans is highly desirable due to the wide range of critical systems which are deployed on FPGAs and may be difficult or costly to remove from operation. Many parallels can be drawn between hardware and natural systems, and one example creates an analogy between hardware attacks and biological attacks. We propose a CRISPR-Cas-inspired (clustered regularly interspaced palindromic repeats) method for detecting hardware Trojans in FPGAs. The fundamental concepts of the Type 1-E CRISPR-Cas mechanism are discussed and simulated to predict the flow of genetic information through this biological system. The basic structure of this system is utilized to propose a novel run-time Trojan detection method titled CADEFT (CRISPR-Cas-based Algorithm for DEtection of FPGA Trojans). Different levels of FPGA application design flow are explored, and CADEFT is proposed for realization at the bitstream level to monitor the configuration bitstream and the run-time properties of the FPGA. The flexibility of CADEFT originates in the CRISPR-Cas mechanisms ability to recognize similar albeit previously unseen patterns which may pose a threat to the system.
rate research
Read More
Internet of Things connects lots of small constrained devices to the Internet. As in any other environment, communication security is important and cryptographic algorithms are one of many elements that we use in order to keep messages secure. Because of the constrained nature of these environments, it is necessary to use algorithms that do not require high computational power. Lightweight ciphers are therefore ideal candidates for this purpose. In this paper, we explore a possibility of attacking an ultra-lightweight cipher PRESENT by using a multiple fault attack. Utilizing the Differential Fault Analysis technique, we were able to recover the secret key with two faulty encryptions and an exhaustive search of 2^16 remaining key bits. Our attack aims at four nibbles in the penultimate round of the cipher, causing faulty output in all nibbles of the output. We also provide a practical attack scenario by exploiting Hardware Trojan (HT) technique for the proposed fault injection in a Xilinx Spartan-6 FPGA.
With the increasing awareness of privacy protection and data fragmentation problem, federated learning has been emerging as a new paradigm of machine learning. Federated learning tends to utilize various privacy preserving mechanisms to protect the transferred intermediate data, among which homomorphic encryption strikes a balance between security and ease of utilization. However, the complicated operations and large operands impose significant overhead on federated learning. Maintaining accuracy and security more efficiently has been a key problem of federated learning. In this work, we investigate a hardware solution, and design an FPGA-based homomorphic encryption framework, aiming to accelerate the training phase in federated learning. The root complexity lies in searching for a compact architecture for the core operation of homomorphic encryption, to suit the requirement of federated learning about high encryption throughput and flexibility of configuration. Our framework implements the representative Paillier homomorphic cryptosystem with high level synthesis for flexibility and portability, with careful optimization on the modular multiplication operation in terms of processing clock cycle, resource usage and clock frequency. Our accelerator achieves a near-optimal execution clock cycle, with a better DSP-efficiency than existing designs, and reduces the encryption time by up to 71% during training process of various federated learning models.
Recent studies show that 20.4% of the internet traffic originates from automated agents. To identify and block such ill-intentioned traffic, mechanisms that verify the humanness of the user are widely deployed, with CAPTCHAs being the most popular. Traditional CAPTCHAs require extra user effort (e.g., solving mathematical puzzles), which can severely downgrade the end-users experience, especially on mobile, and provide sporadic humanness verification of questionable accuracy. More recent solutions like Googles reCAPTCHA v3, leverage user data, thus raising significant privacy concerns. To address these issues, we present zkSENSE: the first zero-knowledge proof-based humanness attestation system for mobile devices. zkSENSE moves the human attestation to the edge: onto the users very own device, where humanness of the user is assessed in a privacy-preserving and seamless manner. zkSENSE achieves this by classifying motion sensor outputs of the mobile device, based on a model trained by using both publicly available sensor data and data collected from a small group of volunteers. To ensure the integrity of the process, the classification result is enclosed in a zero-knowledge proof of humanness that can be safely shared with a remote server. We implement zkSENSE as an Android service to demonstrate its effectiveness and practicality. In our evaluation, we show that zkSENSE successfully verifies the humanness of a user across a variety of attacking scenarios and demonstrates 92% accuracy. On a two years old Samsung S9, zkSENSEs attestation takes around 3 seconds (when visual CAPTCHAs need 9.8 seconds) and consumes a negligible amount of battery.
Multiplication (e.g., convolution) is arguably a cornerstone of modern deep neural networks (DNNs). However, intensive multiplications cause expensive resource costs that challenge DNNs deployment on resource-constrained edge devices, driving several attempts for multiplication-less deep networks. This paper presented ShiftAddNet, whose main inspiration is drawn from a common practice in energy-efficient hardware implementation, that is, multiplication can be instead performed with additions and logical bit-shifts. We leverage this idea to explicitly parameterize deep networks in this way, yielding a new type of deep network that involves only bit-shift and additive weight layers. This hardware-inspired ShiftAddNet immediately leads to both energy-efficient inference and training, without compromising the expressive capacity compared to standard DNNs. The two complementary operation types (bit-shift and add) additionally enable finer-grained control of the models learning capacity, leading to more flexible trade-off between accuracy and (training) efficiency, as well as improved robustness to quantization and pruning. We conduct extensive experiments and ablation studies, all backed up by our FPGA-based ShiftAddNet implementation and energy measurements. Compared to existing DNNs or other multiplication-less models, ShiftAddNet aggressively reduces over 80% hardware-quantified energy cost of DNNs training and inference, while offering comparable or better accuracies. Codes and pre-trained models are available at https://github.com/RICE-EIC/ShiftAddNet.
In machine learning Trojan attacks, an adversary trains a corrupted model that obtains good performance on normal data but behaves maliciously on data samples with certain trigger patterns. Several approaches have been proposed to detect such attacks, but they make undesirable assumptions about the attack strategies or require direct access to the trained models, which restricts their utility in practice. This paper addresses these challenges by introducing a Meta Neural Trojan Detection (MNTD) pipeline that does not make assumptions on the attack strategies and only needs black-box access to models. The strategy is to train a meta-classifier that predicts whether a given target model is Trojaned. To train the meta-model without knowledge of the attack strategy, we introduce a technique called jumbo learning that samples a set of Trojaned models following a general distribution. We then dynamically optimize a query set together with the meta-classifier to distinguish between Trojaned and benign models. We evaluate MNTD with experiments on vision, speech, tabular data and natural language text datasets, and against different Trojan attacks such as data poisoning attack, model manipulation attack, and latent attack. We show that MNTD achieves 97% detection AUC score and significantly outperforms existing detection approaches. In addition, MNTD generalizes well and achieves high detection performance against unforeseen attacks. We also propose a robust MNTD pipeline which achieves 90% detection AUC even when the attacker aims to evade the detection with full knowledge of the system.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
