arXiv subjects

Zhenman Fang

Publications and source records attributed to Zhenman Fang.

25 records · Page 2Linked to original sources

arXiv2022

BDFA: A Blind Data Adversarial Bit-flip Attack on Deep Neural Networks

Adversarial bit-flip attack (BFA) on Neural Network weights can result in catastrophic accuracy degradation by flipping a very small number of bits. A major drawback of prior bit flip attack techniques is their reliance on test data. This is frequently not possible for applications that contain sensitive or proprietary data. In this paper, we propose Blind Data Adversarial Bit-flip Attack (BDFA), a novel technique to enable BFA without any access to the training or testing data. This is achieved by optimizing for a synthetic dataset, which is engineered to match the statistics of batch normalization across different layers of the network and the targeted label. Experimental results show that BDFA could decrease the accuracy of ResNet50 significantly from 75.96\% to 13.94\% with only 4 bits flips.

cs.CR↗

arXiv2021

FitAct: Error Resilient Deep Neural Networks via Fine-Grained Post-Trainable Activation Functions

Deep neural networks (DNNs) are increasingly being deployed in safety-critical systems such as personal healthcare devices and self-driving cars. In such DNN-based systems, error resilience is a top priority since faults in DNN inference could lead to mispredictions and safety hazards. For latency-critical DNN inference on resource-constrained edge devices, it is nontrivial to apply conventional redundancy-based fault tolerance techniques. In this paper, we propose FitAct, a low-cost approach to enhance the error resilience of DNNs by deploying fine-grained post-trainable activation functions. The main idea is to precisely bound the activation value of each individual neuron via neuron-wise bounded activation functions so that it could prevent fault propagation in the network. To avoid complex DNN model re-training, we propose to decouple the accuracy training and resilience training and develop a lightweight post-training phase to learn these activation functions with precise bound values. Experimental results on widely used DNN models such as AlexNet, VGG16, and ResNet50 demonstrate that FitAct outperforms state-of-the-art studies such as Clip-Act and Ranger in enhancing the DNN error resilience for a wide range of fault rates while adding manageable runtime and memory space overheads.

cs.LG↗

arXiv2021

Stealthy Attack on Algorithmic-Protected DNNs via Smart Bit Flipping

Recently, deep neural networks (DNNs) have been deployed in safety-critical systems such as autonomous vehicles and medical devices. Shortly after that, the vulnerability of DNNs were revealed by stealthy adversarial examples where crafted inputs -- by adding tiny perturbations to original inputs -- can lead a DNN to generate misclassification outputs. To improve the robustness of DNNs, some algorithmic-based countermeasures against adversarial examples have been introduced thereafter. In this paper, we propose a new type of stealthy attack on protected DNNs to circumvent the algorithmic defenses: via smart bit flipping in DNN weights, we can reserve the classification accuracy for clean inputs but misclassify crafted inputs even with algorithmic countermeasures. To fool protected DNNs in a stealthy way, we introduce a novel method to efficiently find their most vulnerable weights and flip those bits in hardware. Experimental results show that we can successfully apply our stealthy attack against state-of-the-art algorithmic-protected DNNs.

cs.CR↗

arXiv2021

SeaPlace: Process Variation Aware Placement for Reliable Combinational Circuits against SETs and METs

Nowadays nanoscale combinational circuits are facing significant reliability challenges including soft errors and process variations. This paper presents novel process variation-aware placement strategies that include two algorithms to increase the reliability of combinational circuits against both Single Event Transients (SETs) and Multiple Event Transients (METs). The first proposed algorithm is a global placement method (called SeaPlace-G) that places the cells for hardening the circuit against SETs by solving a quadratic formulation. Afterwards, a detailed placement algorithm (named SeaPlace-D) is proposed to increase the circuit reliability against METs by solving a linear programming optimization problem. Experimental results show that SeaPlace-G and SeaPlace-D averagely achieve 41.78% and 32.04% soft error reliability improvement against SET and MET, respectively. Moreover, when SeaPlace-D is followed by SeaPlace-G, MET reduction can be improved by up to 53.3%.

cs.AR↗

arXiv2018

Best-Effort FPGA Programming: A Few Steps Can Go a Long Way

FPGA-based heterogeneous architectures provide programmers with the ability to customize their hardware accelerators for flexible acceleration of many workloads. Nonetheless, such advantages come at the cost of sacrificing programmability. FPGA vendors and researchers attempt to improve the programmability through high-level synthesis (HLS) technologies that can directly generate hardware circuits from high-level language descriptions. However, reading through recent publications on FPGA designs using HLS, one often gets the impression that FPGA programming is still hard in that it leaves programmers to explore a very large design space with many possible combinations of HLS optimization strategies. In this paper we make two important observations and contributions. First, we demonstrate a rather surprising result: FPGA programming can be made easy by following a simple best-effort guideline of five refinement steps using HLS. We show that for a broad class of accelerator benchmarks from MachSuite, the proposed best-effort guideline improves the FPGA accelerator performance by 42-29,030x. Compared to the baseline CPU performance, the FPGA accelerator performance is improved from an average 292.5x slowdown to an average 34.4x speedup. Moreover, we show that the refinement steps in the best-effort guideline, consisting of explicit data caching, customized pipelining, processing element duplication, computation/communication overlapping and scratchpad reorganization, correspond well to the best practice guidelines for multicore CPU programming. Although our best-effort guideline may not always lead to the optimal solution, it substantially simplifies the FPGA programming effort, and will greatly support the wide adoption of FPGA-based acceleration by the software programming community.

cs.AR↗

arXiv2016

Revisiting FPGA Acceleration of Molecular Dynamics Simulation with Dynamic Data Flow Behavior in High-Level Synthesis

Molecular dynamics (MD) simulation is one of the past decade's most important tools for enabling biology scientists and researchers to explore human health and diseases. However, due to the computation complexity of the MD algorithm, it takes weeks or even months to simulate a comparatively simple biology entity on conventional multicore processors. The critical path in molecular dynamics simulations is the force calculation between particles inside the simulated environment, which has abundant parallelism. Among various acceleration platforms, FPGA is an attractive alternative because of its low power and high energy efficiency. However, due to its high programming cost using RTL, none of the mainstream MD software packages has yet adopted FPGA for acceleration. In this paper we revisit the FPGA acceleration of MD in high-level synthesis (HLS) so as to provide affordable programming cost. Our experience with the MD acceleration demonstrates that HLS optimizations such as loop pipelining, module duplication and memory partitioning are essential to improve the performance, achieving a speedup of 9.5X compared to a 12-core CPU. More importantly, we observe that even the fully optimized HLS design can still be 2X slower than the reference RTL architecture due to the common dynamic (conditional) data flow behavior that is not yet supported by current HLS tools. To support such behavior, we further customize an array of processing elements together with a data-driven streaming network through a common RTL template, and fully automate the design flow. Our final experimental results demonstrate a 19.4X performance speedup and 39X energy efficiency for the widely used ApoA1 MD benchmark on the Convey HC1ex FPGA compared to a 12-core Intel Xeon server.

physics.comp-ph↗

arXiv2016

ARAPrototyper: Enabling Rapid Prototyping and Evaluation for Accelerator-Rich Architectures

Compared to conventional general-purpose processors, accelerator-rich architectures (ARAs) can provide orders-of-magnitude performance and energy gains and are emerging as one of the most promising solutions in the age of dark silicon. However, many design issues related to the complex interaction between general-purpose cores, accelerators, customized on-chip interconnects, and memory systems remain unclear and difficult to evaluate. In this paper we design and implement the ARAPrototyper to enable rapid design space explorations for ARAs in real silicons and reduce the tedious prototyping efforts far down to manageable efforts. First, ARAPrototyper provides a reusable baseline prototype with a highly customizable memory system, including interconnect between accelerators and buffers, interconnect between buffers and last-level cache (LLC) or DRAM, coherency choice at LLC or DRAM, and address translation support. Second, ARAPrototyper provides a clean interface to quickly integrate users' own accelerators written in high-level synthesis (HLS) code. The whole design flow is highly automated to generate a prototype of ARA on an FPGA system-on-chip (SoC). Third, to quickly develop applications that run seamlessly on the ARA prototype, ARAPrototyper provides a system software stack, abstracts the accelerators as software libraries, and provides APIs for software developers. Our experimental results demonstrate that ARAPrototyper enables a wide range of design space explorations for ARAs at manageable prototyping efforts, which has 4,000X to 10,000X faster evaluation time than full-system simulations. We believe that ARAPrototyper can be an attractive alternative for ARA design and evaluation.

cs.AR↗