arXiv subjects

Yuke Zhang

Publications and source records attributed to Yuke Zhang.

28 records · Page 2Linked to original sources

arXiv2023

Making Models Shallow Again: Jointly Learning to Reduce Non-Linearity and Depth for Latency-Efficient Private Inference

Large number of ReLU and MAC operations of Deep neural networks make them ill-suited for latency and compute-efficient private inference. In this paper, we present a model optimization method that allows a model to learn to be shallow. In particular, we leverage the ReLU sensitivity of a convolutional block to remove a ReLU layer and merge its succeeding and preceding convolution layers to a shallow block. Unlike existing ReLU reduction methods, our joint reduction method can yield models with improved reduction of both ReLUs and linear operations by up to 1.73x and 1.47x, respectively, evaluated with ResNet18 on CIFAR-100 without any significant accuracy-drop.

cs.LG↗

arXiv2023

Unconventional polarization switching mechanism in (Hf, Zr)O2 ferroelectrics

HfO$_{2}$-based ferroelectric thin films are promising for their application in ferroelectric devices. Predicting the ultimate magnitude of polarization and understanding its switching mechanism are critical to realize the optimal performance of these devices. Here, a generalized solid-state variable cell nudged elastic band (VCNEB) method is employed to predict the switching pathway associated with domain-wall motion in (Hf, Zr)O$_{2}$ ferroelectrics. It is found that the polarization reversal pathway, where three-fold coordinated O atoms pass across the nominal unit-cell boundaries defined by the Hf/Zr atomic planes, is energetically more favorable than the conventional pathway where the O atoms do not pass through these planes. This finding implies that the polarization orientation in the orthorhombic Pca2$_{1}$ phase of HfO$_{2}$ nd its derivatives is opposite to that normally assumed, predicts the spontaneous polarization magnitude of about 70 $μ$C/cm$^{2}$ that is nearly 50% larger than the commonly accepted value, signifies a positive intrinsic longitudinal piezoelectric coefficient, and suggests growth of ferroelectric domains, in response to an applied electric field, structurally reversed to those usually anticipated. These results provide important insights into the understanding of ferroelectricity in HfO$_{2}$-based ferroelectrics.

cond-mat.mtrl-sci↗

arXiv2023

Matching extension and distance spectral radius

A graph is called $k$-extendable if each $k$-matching can be extended to a perfect matching. We give spectral conditions for the $k$-extendability of graphs and bipartite graphs using Tutte-type and Hall-type structural characterizations. Concretely, we give a sufficient condition in terms of the spectral radius of the distance matrix for the $k$-extendability of a graph and completely characterize the corresponding extremal graphs. A similar result is obtained for bipartite graphs.

math.CO↗

arXiv2023

Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference

The large number of ReLU non-linearity operations in existing deep neural networks makes them ill-suited for latency-efficient private inference (PI). Existing techniques to reduce ReLU operations often involve manual effort and sacrifice significant accuracy. In this paper, we first present a novel measure of non-linearity layers' ReLU sensitivity, enabling mitigation of the time-consuming manual efforts in identifying the same. Based on this sensitivity, we then present SENet, a three-stage training method that for a given ReLU budget, automatically assigns per-layer ReLU counts, decides the ReLU locations for each layer's activation map, and trains a model with significantly fewer ReLUs to potentially yield latency and communication efficient PI. Experimental evaluations with multiple models on various datasets show SENet's superior performance both in terms of reduced ReLUs and improved classification accuracy compared to existing alternatives. In particular, SENet can yield models that require up to ~2x fewer ReLUs while yielding similar accuracy. For a similar ReLU budget SENet can yield models with ~2.32% improved classification accuracy, evaluated on CIFAR-100.

cs.CV↗

arXiv2022

TriLock: IC Protection with Tunable Corruptibility and Resilience to SAT and Removal Attacks

Sequential logic locking has been studied over the last decade as a method to protect sequential circuits from reverse engineering. However, most of the existing sequential logic locking techniques are threatened by increasingly more sophisticated SAT-based attacks, efficiently using input queries to a SAT solver to rule out incorrect keys, as well as removal attacks based on structural analysis. In this paper, we propose TriLock, a sequential logic locking method that simultaneously addresses these vulnerabilities. TriLock can achieve high, tunable functional corruptibility while still guaranteeing exponential queries to the SAT solver in a SAT-based attack. Further, it adopts a state re-encoding method to obscure the boundary between the original state registers and those inserted by the locking method, thus making it more difficult to detect and remove the locking-related components.

cs.CR↗

arXiv2021

Graphs with three distinct distance eigenvalues

In this paper, some special distance spectral properties of graphs are considered. Concretely, we recursively construct an infinite family of trees with distance eigenvalue $-1$, and determine all $\{C_3,C_4\}$-free connected graphs with three distinct distance eigenvalues of which the smallest one is equal to $-3$, which partially answers a problem posed by Koolen, Hayat and Iqbal [Linear Algebra Appl. 505 (2016) 97--108]. Furthermore, we characterize all trees with three distinct distance eigenvalues.

math.CO↗

arXiv2021

Fun-SAT: Functional Corruptibility-Guided SAT-Based Attack on Sequential Logic Encryption

The SAT attack has shown to be efficient against most combinational logic encryption methods. It can be extended to attack sequential logic encryption techniques by leveraging circuit unrolling and model checking methods. However, with no guidance on the number of times that a circuit needs to be unrolled to find the correct key, the attack tends to solve many time-consuming Boolean satisfiability (SAT) and model checking problems, which can significantly hamper its efficiency. In this paper, we introduce Fun-SAT, a functional corruptibility-guided SAT-based attack that can significantly decrease the SAT solving and model checking time of a SAT-based attack on sequential encryption by efficiently estimating the minimum required number of circuit unrollings. Fun-SAT relies on a notion of functional corruptibility for encrypted sequential circuits and its relationship with the required number of circuit unrollings in a SAT-based attack. Numerical results show that Fun-SAT can be, on average, 90x faster than previous attacks against state-of-the-art encryption methods, when both attacks successfully complete before a one-day time-out. Moreover, Fun-SAT completes before the time-out on many more circuits.

cs.CR↗

arXiv2021

Perfect matching and distance spectral radius in graphs and bipartite graphs

A perfect matching in a graph $G$ is a set of nonadjacent edges covering every vertex of $G$. Motivated by recent progress on the relations between the eigenvalues and the matching number of a graph, in this paper, we aim to present a distance spectral radius condition to guarantee the existence of a perfect matching. Let $G$ be an $n$-vertex connected graph where $n$ is even and $λ_{1}(D(G))$ be the distance spectral radius of $G$. Then the following statements are true. \noindent$\rm{I)}$ If $4\le n\le10$ and ${λ}_{1} (D\left(G\right))\le {λ}_{1} (D(S_{n,{\frac{n}{2}}-1}))$, then $G$ contains a perfect matching unless $G\cong S_{n,{\frac{n}{2}-1}}$ where $S_{n,{\frac{n}{2}-1}}\cong K_{{\frac{n}{2}-1}}\vee ({\frac{n}{2}+1})K_1$. \noindent$\rm{II)}$ If $n\ge 12$ and ${λ}_{1} (D\left(G\right))\le {λ}_{1} (D(G^*))$, then $G$ contains a perfect matching unless $G\cong G^*$ where $G^*\cong K_1\vee (K_{n-3}\cup2K_1)$. Moreover, if $G$ is a connected $2n$-vertex balanced bipartite graph with $λ_{1}(D(G))\le λ_{1}(D(B_{n-1,n-2})) $, then $G$ contains a perfect matching, unless $G\cong B_{n-1,n-2}$ where $B_{n-1,n-2}$ is obtained from $K_{n,n-2}$ by attaching two pendent vertices to a vertex in the $n$-vertex part.

math.CO↗

arXiv2020

Effects of Strain and Film Thickness on the Stability of the Rhombohedral Phase of HfO2

The discovery of ferroelectric polarization in HfO2-based ultrathin films has spawned a lot of interest due to their potential applications in data storage. Recently, a new R3m rhombohedral phase was proposed to be responsible for the emergence of ferroelectricity in the [111]-oriented Hf0.5Zr0.5O2 thin films, but the fundamental mechanism of ferroelectric polarization in such films remains poorly understood. In this paper, we employ density-functional-theory calculations to investigate structural and polarization properties of the R3m HfO2 phase. We find that the film thickness and in-plane compressive strain effects play a key role in stabilizing the R3m phase leading to robust ferroelectricity of [111]-oriented R3m HfO2.

cond-mat.mtrl-sci↗

arXiv2018

Deep Compression of Sum-Product Networks on Tensor Networks

Sum-product networks (SPNs) represent an emerging class of neural networks with clear probabilistic semantics and superior inference speed over graphical models. This work reveals a strikingly intimate connection between SPNs and tensor networks, thus leading to a highly efficient representation that we call tensor SPNs (tSPNs). For the first time, through mapping an SPN onto a tSPN and employing novel optimization techniques, we demonstrate remarkable parameter compression with negligible loss in accuracy.

cs.LG↗