Matching Items (4)
Filtering by
- All Subjects: adversarial attack
- Creators: Seo, Jae-Sun
- Creators: Long, Yu
Description
A 4-phase, quasi-current-mode hysteretic buck converter with digital frequency synchronization, online comparator offset-calibration and digital current sharing control is presented. The switching frequency of the hysteretic converter is digitally synchronized to the input clock reference with less than ±1.5% error in the switching frequency range of 3-9.5MHz. The online offset calibration cancels the input-referred offset of the hysteretic comparator and enables ±1.1% voltage regulation accuracy. Maximum current-sharing error of ±3.6% is achieved by a duty-cycle-calibrated delay line based PWM generator, without affecting the phase synchronization timing sequence. In light load conditions, individual converter phases can be disabled, and the final stage power converter output stage is segmented for high efficiency. The DC-DC converter achieves 93% peak efficiency for Vi = 2V and Vo = 1.6V.
ContributorsSun, Ming (Author) / Bakkaloglu, Bertan (Thesis advisor) / Garrity, Douglas (Committee member) / Seo, Jae-Sun (Committee member) / Kitchen, Jennifer (Committee member) / Arizona State University (Publisher)
Created2017
Description
Adversarial threats of deep learning are increasingly becoming a concern due to the ubiquitous deployment of deep neural networks(DNNs) in many security-sensitive domains. Among the existing threats, adversarial weight perturbation is an emerging class of threats that attempts to perturb the weight parameters of DNNs to breach security and privacy.In this thesis, the first weight perturbation attack introduced is called Bit-Flip Attack (BFA), which can maliciously flip a small number of bits within a computer’s main memory system storing the DNN weight parameter to achieve malicious objectives. Our developed algorithm can achieve three specific attack objectives: I) Un-targeted accuracy degradation attack, ii) Targeted attack, & iii) Trojan attack. Moreover, BFA utilizes the rowhammer technique to demonstrate the bit-flip attack in an actual computer prototype. While the bit-flip attack is conducted in a white-box setting, the subsequent contribution of this thesis is to develop another novel weight perturbation attack in a black-box setting. Consequently, this thesis discusses a new study of DNN model vulnerabilities in a multi-tenant Field Programmable Gate Array (FPGA) cloud under a strict black-box framework. This newly developed attack framework injects faults in the malicious tenant by duplicating specific DNN weight packages during data transmission between off-chip memory and on-chip buffer of a victim FPGA. The proposed attack is also experimentally validated in a multi-tenant cloud FPGA prototype. In the final part, the focus shifts toward deep learning model privacy, popularly known as model extraction, that can steal partial DNN weight parameters remotely with the aid of a memory side-channel attack. In addition, a novel training algorithm is designed to utilize the partially leaked DNN weight bit information, making the model extraction attack more effective. The algorithm effectively leverages the partial leaked bit information and generates a substitute prototype of the victim model with almost identical performance to the victim.
ContributorsRakin, Adnan Siraj (Author) / Fan, Deliang (Thesis advisor) / Chakrabarti, Chaitali (Committee member) / Seo, Jae-Sun (Committee member) / Cao, Yu (Committee member) / Arizona State University (Publisher)
Created2022
Description
Point of Load (POL) DC-DC converters are increasingly used in space applications, data centres, electric vehicles, portable computers and devices and medical electronics. Heavy computing and processing capabilities of the modern devices have ushered the use of higher battery supply voltage to increase power storage. The need to address this consumer experience driven requirement has propelled the evolution of the next generation of small form-factor power converters which can operate with higher step down ratios while supplying heavy continuous load currents without sacrificing efficiency. Constant On-Time (COT) converter topology is capable of achieving stable operation at high conversion ratio with minimum off-chip components and small silicon area. This work proposes a Constant On-Time buck dc-dc converter for a wide dynamic input range and load currents from 100mA to 10A. Accuracy of this ripple based converter is improved by a unique voltage positioning technique which modulates the reference voltage to lower the average ripple profile close to the nominal output. Adaptive On-time block features a transient enhancement scheme to assist in faster voltage droop recovery when the output voltage dips below a defined threshold. UtilizingGallium Nitride (GaN) power switches enable the proposed converter to achieve very high efficiency while using smaller size inductor-capacitor (LC) power-stage. Use of novel Superjunction devices with higher drain-source blocking voltage simplifies the complex driver design and enables faster frequency of operation. It allows 1.8VComplementary Metal-Oxide Semiconductor (CMOS) devices to effectively drive GaNpower FETs which require 5V gate signal swing. The presented controller circuit uses internal ripple generation which reduces reliance on output cap equivalent series resistance (ESR) for loop stability and facilitates ripples reduction at the output. The ripple generation network is designed to provide ai
optimally stable performance while maintaining load regulation and line regulation accuracy withing specified margin. The chip with ts external Power FET package is proposed to be integrated on a printed circuit board for testing. The designed power converter is expected to operate under 200 MRad of a total ionising dose of radiation enabling it to function within large hadron collider at CERN and space satellite and probe missions.
optimally stable performance while maintaining load regulation and line regulation accuracy withing specified margin. The chip with ts external Power FET package is proposed to be integrated on a printed circuit board for testing. The designed power converter is expected to operate under 200 MRad of a total ionising dose of radiation enabling it to function within large hadron collider at CERN and space satellite and probe missions.
ContributorsJoshi, Omkar (Author) / Bakkaloglu, Bertan (Thesis advisor) / Kitchen, Jennifer (Committee member) / Long, Yu (Committee member) / Arizona State University (Publisher)
Created2019
Description
The advances of Deep Learning (DL) achieved recently have successfully demonstrated its great potential of surpassing or close to human-level performance across multiple domains. Consequently, there exists a rising demand to deploy state-of-the-art DL algorithms, e.g., Deep Neural Networks (DNN), in real-world applications to release labors from repetitive work. On the one hand, the impressive performance achieved by the DNN normally accompanies with the drawbacks of intensive memory and power usage due to enormous model size and high computation workload, which significantly hampers their deployment on the resource-limited cyber-physical systems or edge devices. Thus, the urgent demand for enhancing the inference efficiency of DNN has also great research interests across various communities. On the other hand, scientists and engineers still have insufficient knowledge about the principles of DNN which makes it mostly be treated as a black-box. Under such circumstance, DNN is like "the sword of Damocles" where its security or fault-tolerance capability is an essential concern which cannot be circumvented.
Motivated by the aforementioned concerns, this dissertation comprehensively investigates the emerging efficiency and security issues of DNNs, from both software and hardware design perspectives. From the efficiency perspective, as the foundation technique for efficient inference of target DNN, the model compression via quantization is elaborated. In order to maximize the inference performance boost, the deployment of quantized DNN on the revolutionary Computing-in-Memory based neural accelerator is presented in a cross-layer (device/circuit/system) fashion. From the security perspective, the well known adversarial attack is investigated spanning from its original input attack form (aka. Adversarial example generation) to its parameter attack variant.
Motivated by the aforementioned concerns, this dissertation comprehensively investigates the emerging efficiency and security issues of DNNs, from both software and hardware design perspectives. From the efficiency perspective, as the foundation technique for efficient inference of target DNN, the model compression via quantization is elaborated. In order to maximize the inference performance boost, the deployment of quantized DNN on the revolutionary Computing-in-Memory based neural accelerator is presented in a cross-layer (device/circuit/system) fashion. From the security perspective, the well known adversarial attack is investigated spanning from its original input attack form (aka. Adversarial example generation) to its parameter attack variant.
Contributorshe, zhezhi (Author) / Fan, Deliang (Thesis advisor) / Chakrabarti, Chaitali (Committee member) / Cao, Yu (Committee member) / Seo, Jae-Sun (Committee member) / Arizona State University (Publisher)
Created2020