Wenting Li

Aleksandra Burashnikova, Wenting Li, Massih Amini et al.

Climate change increases the number of extreme weather events (wind and snowstorms, heavy rains, wildfires) that compromise power system reliability and lead to multiple equipment failures. Real-time and accurate detecting of potential line failures is the first step to mitigating the extreme weather impact and activating emergency controls. Power balance equations nonlinearity, increased uncertainty in generation during extreme events, and lack of grid observability compromise the efficiency of traditional data-driven failure detection methods. At the same time, modern problem-oblivious machine learning methods based on neural networks require a large amount of data to detect an accident, especially in a time-changing environment. This paper proposes a Physics-InformEd Line failure Detector (FIELD) that leverages grid topology information to reduce sample and time complexities and improve localization accuracy. Finally, we illustrate the superior empirical performance of our approach compared to state-of-the-art methods over various test cases.

Dongyang Kuang, Craig Michoski, Wenting Li et al.

In this work, a parameter-efficient attention module is presented for emotion classification using a limited, or relatively small, number of electroencephalogram (EEG) signals. This module is called the Monotonicity Constrained Attention Module (MCAM) due to its capability of incorporating priors on the monotonicity when converting features' Gram matrices into attention matrices for better feature refinement. Our experiments have shown that MCAM's effectiveness is comparable to state-of-the-art attention modules in boosting the backbone network's performance in prediction while requiring less parameters. Several accompanying sensitivity analyses on trained models' prediction concerning different attacks are also performed. These attacks include various frequency domain filtering levels and gradually morphing between samples associated with multiple labels. Our results can help better understand different modules' behaviour in prediction and can provide guidance in applications where data is limited and are with noises.

Miao Li, Michael Klamkin, Pascal Van Hentenryck et al.

This paper studies optimization proxies, machine learning (ML) models trained to efficiently predict optimal solutions for AC Optimal Power Flow (ACOPF) problems. While promising, optimization proxy performance heavily depends on training data quality. To address this limitation, this paper introduces a novel active sampling framework for ACOPF optimization proxies designed to generate realistic and diverse training data. The framework actively explores varied, flexible problem specifications reflecting plausible operational realities. More importantly, the approach uses optimization-specific quantities (active constraint sets) that better capture the salient features of an ACOPF that lead to the optimal solution. Numerical results show superior generalization over existing sampling methods with an equivalent training budget, significantly advancing the state-of-practice for trustworthy ACOPF optimization proxies.

Henry Tischler, Wenting Li, Qi Tang et al.

Accurate knowledge of the atomistic transition pathways in materials and material surfaces is crucial for many material science problems. However, conventional simulation techniques used to find these transitions are extremely computationally intensive. Even with large-scale, accelerated material simulations, the computational cost constrains the applicable domain in practice. Machine learning models, with the potential to learn the complex emergent behaviors governing atomistic transitions as a fast surrogate model, have great promise to predict transitions with a vastly reduced computational cost. Here, we demonstrate how transformers can be trained to predict atomistic transitions in nano-clusters. We show how we evaluate physical validity of the predictions and how a multitude of additional, different microstates can be generated by slightly varying the data provided to the model.

Ziyang Chen, Yongjun Zhang, Wenting Li et al.

Real-world applications of stereo matching, such as autonomous driving, place stringent demands on both safety and accuracy. However, learning-based stereo matching methods inherently suffer from the loss of geometric structures in certain feature channels, creating a bottleneck in achieving precise detail matching. Additionally, these methods lack interpretability due to the black-box nature of deep learning. In this paper, we propose MoCha-V2, a novel learning-based paradigm for stereo matching. MoCha-V2 introduces the Motif Correlation Graph (MCG) to capture recurring textures, which are referred to as ``motifs" within feature channels. These motifs reconstruct geometric structures and are learned in a more interpretable way. Subsequently, we integrate features from multiple frequency domains through wavelet inverse transformation. The resulting motif features are utilized to restore geometric structures in the stereo matching process. Experimental results demonstrate the effectiveness of MoCha-V2. MoCha-V2 achieved 1st place on the Middlebury benchmark at the time of its release. Code is available at https://github.com/ZYangChen/MoCha-Stereo.

Wenting Li, Jiahong Xue, Xi Zhang et al.

Word embedding has become ubiquitous and is widely used in various natural language processing (NLP) tasks, such as web retrieval, web semantic analysis, and machine translation, and so on. Unfortunately, training the word embedding in a relatively large corpus is prohibitively expensive. We propose a graph-based word embedding algorithm, called Word-Graph2vec, which converts the large corpus into a word co-occurrence graph, then takes the word sequence samples from this graph by randomly traveling and trains the word embedding on this sampling corpus in the end. We posit that because of the limited vocabulary, huge idioms, and fixed expressions in English, the size and density of the word co-occurrence graph change slightly with the increase in the training corpus. So that Word-Graph2vec has stable runtime on the large-scale data set, and its performance advantage becomes more and more obvious with the growth of the training corpus. Extensive experiments conducted on real-world datasets show that the proposed algorithm outperforms traditional Word2vec four to five times in terms of efficiency and two to three times than FastText, while the error generated by the random walk technique is small.

Ziyang Chen, Wenting Li, Yongjun Zhang et al.

Constrained by the low-rank bottleneck inherent in attention mechanisms, current stereo matching transformers suffer from limited nonlinear expressivity, which renders their feature representations sensitive to challenging conditions such as reflections. To overcome this difficulty, we present the Hadamard Attention Recurrent Stereo Transformer (HART). HART includes a novel attention mechanism that incorporates the following components: 1) The Dense Attention Kernel (DAK) maps the attention weight distribution into a high-dimensional space over (0, +$\infty$). By removing the upper bound constraint on attention weights, DAK enables more flexible modeling of complex feature interactions. This reduces feature collinearity. 2) The Multi Kernel & Order Interaction (MKOI) module extends the attention mechanism by unifying semantic and spatial knowledge learning. This integration improves the ability of HART to learn features in binocular images. Experimental results demonstrate the effectiveness of our HART. In reflective area, HART ranked 1st on the KITTI 2012 benchmark among all published methods at the time of submission. Code is available at https://github.com/ZYangChen/HART.

Mohamad Fares El Hajj Chehade, Wenting Li, Brian W. Bell et al.

The robustness of neural networks is crucial in safety-critical applications, where identifying a reliable input space is essential for effective model selection, robustness evaluation, and the development of reliable control strategies. Most existing robustness verification methods assess the worst-case output under the assumption that the input space is known. However, precisely identifying a verifiable input space \(\mathcal{C}\), where no adversarial examples exist, is challenging due to the possible high dimensionality, discontinuity, and non-convex nature of the input space. To address this challenge, we propose a novel framework, **LEVIS**, consisting of **LEVIS-α** and **LEVIS-\b{eta}**. **LEVIS-α** identifies a single, large verifiable ball that intersects at least two boundaries of a bounded region \(\mathcal{C}\), while **LEVIS-\b{eta}** systematically captures the entirety of the verifiable space by integrating multiple verifiable balls. Our contributions include: (1) introducing a verification framework that uses mixed-integer programming (MIP) to compute nearest and directional adversarial points, (2) integrating complementarity-constrained (CC) optimization with a reduced MIP formulation for scalability, achieving up to a 6 times runtime reduction, (3) theoretically characterizing the properties of the verifiable balls obtained by **LEVIS-α**, and (4) validating the approach across applications including electrical power flow regression and image classification, with demonstrated performance gains and geometric insights into the verifiable region.

Joe Gorka, Tim Hsu, Wenting Li et al.

Higher variability in grid conditions, resulting from growing renewable penetration and increased incidence of extreme weather events, has increased the difficulty of screening for scenarios that may lead to catastrophic cascading failures. Traditional power-flow-based tools for assessing cascading blackout risk are too slow to properly explore the space of possible failures and load/generation patterns. We add to the growing literature of faster graph-neural-network (GNN)-based techniques, developing two novel techniques for the estimation of blackout magnitude from initial grid conditions. First we propose several methods for employing an initial classification step to filter out safe "non blackout" scenarios prior to magnitude estimation. Second, using insights from the statistical properties of cascading blackouts, we propose a method for facilitating non-local message passing in our GNN models. We validate these two approaches on a large simulated dataset, and show the potential of both to increase blackout size estimation performance.

Wenting Li, Saif R. Kazi, Russell Bent et al.

Neural networks achieve strong empirical performance, but robustness concerns still hinder deployment in safety-critical applications. Formal verification provides robustness guarantees, but current methods face a scalability-completeness trade-off. We propose a hybrid verifier in a branch-and-bound (BaB) framework that efficiently tightens both upper and lower bounds until an $ε-$global optimum is reached or early stop is triggered. The key is an exact nonlinear program with complementarity constraints (NLP-CC) for upper bounding that preserves the ReLU input-output graph, so any feasible solution yields a valid counterexample and enables rapid pruning of unsafe subproblems. We further accelerate verification with (i) warm-started NLP solves requiring minimal constraint-matrix updates and (ii) pattern-aligned strong branching that prioritizes splits most effective at tightening relaxations. We also provide conditions under which NLP-CC upper bounds are tight. Experiments on MNIST and CIFAR-10 show markedly tighter upper bounds than PGD across perturbation radii spanning up to three orders of magnitude, fast per-node solves in practice, and substantial end-to-end speedups over MIP-based verification, amplified by warm-starting, GPU batching, and pattern-aligned branching.

Wenting Li, Deepjyoti Deka

Electrical faults may trigger blackouts or wildfires without timely monitoring and control strategy. Traditional solutions for locating faults in distribution systems are not real-time when network observability is low, while novel black-box machine learning methods are vulnerable to stochastic environments. We propose a novel Physics-Preserved Graph Network (PPGN) architecture to accurately locate faults at the node level with limited observability and labeled training data. PPGN has a unique two-stage graph neural network architecture. The first stage learns the graph embedding to represent the entire network using a few measured nodes. The second stage finds relations between the labeled and unlabeled data samples to further improve the location accuracy. We explain the benefits of the two-stage graph configuration through a random walk equivalence. We numerically validate the proposed method in the IEEE 123-node and 37-node test feeders, demonstrating the superior performance over three baseline classifiers when labeled training data is limited, and loads and topology are allowed to vary.

Yongyi Guo, Dominic Coey, Mikael Konutgan et al.

We consider the problem of variance reduction in randomized controlled trials, through the use of covariates correlated with the outcome but independent of the treatment. We propose a machine learning regression-adjusted treatment effect estimator, which we call MLRATE. MLRATE uses machine learning predictors of the outcome to reduce estimator variance. It employs cross-fitting to avoid overfitting biases, and we prove consistency and asymptotic normality under general conditions. MLRATE is robust to poor predictions from the machine learning step: if the predictions are uncorrelated with the outcomes, the estimator performs asymptotically no worse than the standard difference-in-means estimator, while if predictions are highly correlated with outcomes, the efficiency gains are large. In A/A tests, for a set of 48 outcome metrics commonly monitored in Facebook experiments the estimator has over 70% lower variance than the simple difference-in-means estimator, and about 19% lower variance than the common univariate procedure which adjusts only for pre-experiment values of the outcome.

Michael Rodler, Wenting Li, Ghassan O. Karame et al.

Recent attacks exploiting errors in smart contract code had devastating consequences thereby questioning the benefits of this technology. It is currently highly challenging to fix errors and deploy a patched contract in time. Instant patching is especially important since smart contracts are always online due to the distributed nature of blockchain systems. They also manage considerable amounts of assets, which are at risk and often beyond recovery after an attack. Existing solutions to upgrade smart contracts depend on manual and error-prone processes. This paper presents a framework, called EVMPatch, to instantly and automatically patch faulty smart contracts. EVMPatch features a bytecode rewriting engine for the popular Ethereum blockchain, and transparently/automatically rewrites common off-the-shelf contracts to upgradable contracts. The proof-of-concept implementation of EVMPatch automatically hardens smart contracts that are vulnerable to integer over/underflows and access control errors, but can be easily extended to cover more bug classes. Our extensive evaluation on 14,000 real-world (vulnerable) contracts demonstrate that our approach successfully blocks attack transactions launched on these contracts, while keeping the intended functionality of the contract intact. We perform a study with experienced software developers, showing that EVMPatch is practical, and reduces the time for converting a given Solidity smart contract to an upgradable contract by 97.6 %, while ensuring functional equivalence to the original contract.

Michael Rodler, Wenting Li, Ghassan O. Karame et al.

Recently, a number of existing blockchain systems have witnessed major bugs and vulnerabilities within smart contracts. Although the literature features a number of proposals for securing smart contracts, these proposals mostly focus on proving the correctness or absence of a certain type of vulnerability within a contract, but cannot protect deployed (legacy) contracts from being exploited. In this paper, we address this problem in the context of re-entrancy exploits and propose a novel smart contract security technology, dubbed Sereum (Secure Ethereum), which protects existing, deployed contracts against re-entrancy attacks in a backwards compatible way based on run-time monitoring and validation. Sereum does neither require any modification nor any semantic knowledge of existing contracts. By means of implementation and evaluation using the Ethereum blockchain, we show that Sereum covers the actual execution flow of a smart contract to accurately detect and prevent attacks with a false positive rate as small as 0.06% and with negligible run-time overhead. As a by-product, we develop three advanced re-entrancy attacks to demonstrate the limitations of existing offline vulnerability analysis tools.

Wenting Li, Deepjyoti Deka, Michael Chertkov et al.

Diverse fault types, fast re-closures, and complicated transient states after a fault event make real-time fault location in power grids challenging. Existing localization techniques in this area rely on simplistic assumptions, such as static loads, or require much higher sampling rates or total measurement availability. This paper proposes a faulted line localization method based on a Convolutional Neural Network (CNN) classifier using bus voltages. Unlike prior data-driven methods, the proposed classifier is based on features with physical interpretations that improve the robustness of the location performance. The accuracy of our CNN based localization tool is demonstrably superior to other machine learning classifiers in the literature. To further improve the location performance, a joint phasor measurement units (PMU) placement strategy is proposed and validated against other methods. A significant aspect of our methodology is that under very low observability (7% of buses), the algorithm is still able to localize the faulted line to a small neighborhood with high probability. The performance of our scheme is validated through simulations of faults of various types in the IEEE 39-bus and 68-bus power systems under varying uncertain conditions, system observability, and measurement quality.

Claudio Soriente, Ghassan Karame, Wenting Li et al.

With the proliferation of Trusted Execution Environments (TEEs) such as Intel SGX, a number of cloud providers will soon introduce TEE capabilities within their offering (e.g., Microsoft Azure). Although the integration of SGX within the cloud considerably strengthens the threat model for cloud applications, the current model to deploy and provision enclaves prevents the cloud operator from adding or removing enclaves dynamically - thus preventing elasticity for TEE-based applications in the cloud. In this paper, we propose ReplicaTEE, a solution that enables seamless provisioning and decommissioning of TEE-based applications in the cloud. ReplicaTEE leverages an SGX-based provisioning layer that interfaces with a Byzantine Fault-Tolerant storage service to securely orchestrate enclave replication in the cloud, without the active intervention of the application owner. Namely, in ReplicaTEE, the application owner entrusts application secret to the provisioning layer; the latter handles all enclave commissioning and de-commissioning operations throughout the application lifetime. We analyze the security of ReplicaTEE and show that it is secure against attacks by a powerful adversary that can compromise a large fraction of the cloud infrastructure. We implement a prototype of ReplicaTEE in a realistic cloud environment and evaluate its performance. ReplicaTEE moderately increments the TCB by ~800 LoC. Our evaluation shows that ReplicaTEE does not add significant overhead to existing SGX-based applications.

Jian Liu, Wenting Li, Ghassan O. Karame et al.

The surging interest in blockchain technology has revitalized the search for effective Byzantine consensus schemes. In particular, the blockchain community has been looking for ways to effectively integrate traditional Byzantine fault-tolerant (BFT) protocols into a blockchain consensus layer allowing various financial institutions to securely agree on the order of transactions. However, existing BFT protocols can only scale to tens of nodes due to their $O(n^2)$ message complexity. In this paper, we propose FastBFT, a fast and scalable BFT protocol. At the heart of FastBFT is a novel message aggregation technique that combines hardware-based trusted execution environments (TEEs) with lightweight secret sharing primitives. Combining this technique with several other optimizations (i.e., optimistic execution, tree topology and failure detection), FastBFT achieves low latency and high throughput even for large scale networks. Via systematic analysis and experiments, we demonstrate that FastBFT has better scalability and performance than previous BFT protocols.

Jian Liu, Wenting Li, Ghassan O. Karame et al.

Motivated by the great success and adoption of Bitcoin, a number of cryptocurrencies such as Litecoin, Dogecoin, and Ethereum are becoming increasingly popular. Although existing blockchain-based cryptocurrency schemes can ensure reasonable security for transactions, they do not consider any notion of fairness. Fair exchange allows two players to exchange digital "items", such as digital signatures, over insecure networks fairly, so that either each player gets the other's item, or neither player does. Given that blockchain participants typically do not trust each other, enabling fairness in existing cryptocurrencies is an essential but insufficiently explored problem. In this paper, we explore the solution space for enabling the fair exchange of a cryptocurrency payment for a receipt. We identify the timeliness of an exchange as an important property especially when one of the parties involved in the exchange is resource-constrained. We introduce the notion of strong timeliness for a fair exchange protocol and propose two fair payment-for-receipt protocol instantiations that leverage functionality of the blockchain to achieve strong timeliness. We implement both and compare their security and efficiency.

Jens Mathias Bohli, Dan Dobre, Ghassan O. Karame et al.

Location-based services are increasingly used in our daily activities. In current services, users however have to give up their location privacy in order to acquire the service. The literature features a large number of contributions which aim at enhancing user privacy in location-based services. Most of these contributions obfuscate the locations of users using spatial and/or temporal cloaking in order to provide k-anonymity. Although such schemes can indeed strengthen the location privacy of users, they often decrease the service quality and do not necessarily prevent the possible tracking of user movements (i.e., direction, trajectory, velocity). With the rise of Geofencing applications, tracking of movements becomes more evident since, in these settings, the service provider is not only requesting a single location of the user, but requires the movement vectors of users to determine whether the user has entered/exited a Geofence of interest. In this paper, we propose a novel solution, PrivLoc, which enables the privacy-preserving outsourcing of Geofencing and location-based services to the cloud without leaking any meaningful information about the location, trajectory, and velocity of the users. Notably, PrivLoc enables an efficient and privacy-preserving intersection of movement vectors with any polygon of interest, leveraging functionality from existing Geofencing services or spatial databases. We analyze the security and privacy provisions of PrivLoc and we evaluate the performance of our scheme by means of implementation. Our results show that the performance overhead introduced by PrivLoc can be largely tolerated in realistic deployment settings.