arXiv subjects

Xinda Li

Publications and source records attributed to Xinda Li.

8 recordsLinked to original sources

arXiv2026

When expectation fails: stochastic MPC of linear systems with random input losses

We consider stochastic model predictive control (MPC) for constrained linear systems subject to multiplicative binary input uncertainty, motivated by applications such as networked control with packet losses and intermittent actuation. A common approach in this setting replaces the stochastic dynamics with their expectation, yielding tractable formulations that admit standard terminal ingredients and stability guarantees in expectation. We show that such formulations can exhibit structural properties that differ fundamentally from those of deterministic MPC and may be misleading as indicators of realized closed-loop behaviour. In particular, the expected value function is not necessarily monotonic in the prediction horizon, and value function-based inner approximations of the region of attraction may deteriorate as the horizon increases. Furthermore, we establish a probabilistic comparison with certainty-equivalent (optimistic) MPC, showing that the latter can ensure a strictly positive probability of recursive feasibility in situations where stochastic MPC certifies feasibility but fails with probability one. These results highlight inherent limitations of expectation-based stochastic MPC for systems with multiplicative binary uncertainty and motivate a re-examination of how stochasticity is incorporated into constrained predictive control design for such systems.

eess.SY↗

arXiv2023

PEPSI: Practically Efficient Private Set Intersection in the Unbalanced Setting

Two parties with private data sets can find shared elements using a Private Set Intersection (PSI) protocol without revealing any information beyond the intersection. Circuit PSI protocols privately compute an arbitrary function of the intersection - such as its cardinality, and are often employed in an unbalanced setting where one party has more data than the other. Existing protocols are either computationally inefficient or require extensive server-client communication on the order of the larger set. We introduce Practically Efficient PSI or PEPSI, a non-interactive solution where only the client sends its encrypted data. PEPSI can process an intersection of 1024 client items with a million server items in under a second, using less than 5 MB of communication. Our work is over 4 orders of magnitude faster than an existing non-interactive circuit PSI protocol and requires only 10% of the communication. It is also up to 20 times faster than the work of Ion et al., which computes a limited set of functions and has communication costs proportional to the larger set. Our work is the first to demonstrate that non-interactive circuit PSI can be practically applied in an unbalanced setting.

cs.CR↗

arXiv2023

TACOformer:Token-channel compounded Cross Attention for Multimodal Emotion Recognition

Recently, emotion recognition based on physiological signals has emerged as a field with intensive research. The utilization of multi-modal, multi-channel physiological signals has significantly improved the performance of emotion recognition systems, due to their complementarity. However, effectively integrating emotion-related semantic information from different modalities and capturing inter-modal dependencies remains a challenging issue. Many existing multimodal fusion methods ignore either token-to-token or channel-to-channel correlations of multichannel signals from different modalities, which limits the classification capability of the models to some extent. In this paper, we propose a comprehensive perspective of multimodal fusion that integrates channel-level and token-level cross-modal interactions. Specifically, we introduce a unified cross attention module called Token-chAnnel COmpound (TACO) Cross Attention to perform multimodal fusion, which simultaneously models channel-level and token-level dependencies between modalities. Additionally, we propose a 2D position encoding method to preserve information about the spatial distribution of EEG signal channels, then we use two transformer encoders ahead of the fusion module to capture long-term temporal dependencies from the EEG signal and the peripheral physiological signal, respectively. Subject-independent experiments on emotional dataset DEAP and Dreamer demonstrate that the proposed model achieves state-of-the-art performance.

cs.MM↗

arXiv2023

Fast and Private Inference of Deep Neural Networks by Co-designing Activation Functions

Machine Learning as a Service (MLaaS) is an increasingly popular design where a company with abundant computing resources trains a deep neural network and offers query access for tasks like image classification. The challenge with this design is that MLaaS requires the client to reveal their potentially sensitive queries to the company hosting the model. Multi-party computation (MPC) protects the client's data by allowing encrypted inferences. However, current approaches suffer from prohibitively large inference times. The inference time bottleneck in MPC is the evaluation of non-linear layers such as ReLU activation functions. Motivated by the success of previous work co-designing machine learning and MPC, we develop an activation function co-design. We replace all ReLUs with a polynomial approximation and evaluate them with single-round MPC protocols, which give state-of-the-art inference times in wide-area networks. Furthermore, to address the accuracy issues previously encountered with polynomial activations, we propose a novel training algorithm that gives accuracy competitive with plaintext models. Our evaluation shows between $3$ and $110\times$ speedups in inference time on large models with up to $23$ million parameters while maintaining competitive inference accuracy.

cs.CR↗

arXiv2022

Towards Robust Dataset Learning

Adversarial training has been actively studied in recent computer vision research to improve the robustness of models. However, due to the huge computational cost of generating adversarial samples, adversarial training methods are often slow. In this paper, we study the problem of learning a robust dataset such that any classifier naturally trained on the dataset is adversarially robust. Such a dataset benefits the downstream tasks as natural training is much faster than adversarial training, and demonstrates that the desired property of robustness is transferable between models and data. In this work, we propose a principled, tri-level optimization to formulate the robust dataset learning problem. We show that, under an abstraction model that characterizes robust vs. non-robust features, the proposed method provably learns a robust dataset. Extensive experiments on MNIST, CIFAR10, and TinyImageNet demostrate the effectiveness of our algorithm with different network initializations and architectures.

cs.CV↗

arXiv2022

Recovery from Non-Decomposable Distance Oracles

A line of work has looked at the problem of recovering an input from distance queries. In this setting, there is an unknown sequence $s \in \{0,1\}^{\leq n}$, and one chooses a set of queries $y \in \{0,1\}^{\mathcal{O}(n)}$ and receives $d(s,y)$ for a distance function $d$. The goal is to make as few queries as possible to recover $s$. Although this problem is well-studied for decomposable distances, i.e., distances of the form $d(s,y) = \sum_{i=1}^n f(s_i, y_i)$ for some function $f$, which includes the important cases of Hamming distance, $\ell_p$-norms, and $M$-estimators, to the best of our knowledge this problem has not been studied for non-decomposable distances, for which there are important special cases such as edit distance, dynamic time warping (DTW), Frechet distance, earth mover's distance, and so on. We initiate the study and develop a general framework for such distances. Interestingly, for some distances such as DTW or Frechet, exact recovery of the sequence $s$ is provably impossible, and so we show by allowing the characters in $y$ to be drawn from a slightly larger alphabet this then becomes possible. In a number of cases we obtain optimal or near-optimal query complexity. We also study the role of adaptivity for a number of different distance functions. One motivation for understanding non-adaptivity is that the query sequence can be fixed and the distances of the input to the queries provide a non-linear embedding of the input, which can be used in downstream applications involving, e.g., neural networks for natural language processing.

cs.DS↗

arXiv2021

SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version)

Deep Neural Network (DNN) watermarking is a method for provenance verification of DNN models. Watermarking should be robust against watermark removal attacks that derive a surrogate model that evades provenance verification. Many watermarking schemes that claim robustness have been proposed, but their robustness is only validated in isolation against a relatively small set of attacks. There is no systematic, empirical evaluation of these claims against a common, comprehensive set of removal attacks. This uncertainty about a watermarking scheme's robustness causes difficulty to trust their deployment in practice. In this paper, we evaluate whether recently proposed watermarking schemes that claim robustness are robust against a large set of removal attacks. We survey methods from the literature that (i) are known removal attacks, (ii) derive surrogate models but have not been evaluated as removal attacks, and (iii) novel removal attacks. Weight shifting and smooth retraining are novel removal attacks adapted to the DNN watermarking schemes surveyed in this paper. We propose taxonomies for watermarking schemes and removal attacks. Our empirical evaluation includes an ablation study over sets of parameters for each attack and watermarking scheme on the CIFAR-10 and ImageNet datasets. Surprisingly, none of the surveyed watermarking schemes is robust in practice. We find that schemes fail to withstand adaptive attacks and known methods for deriving surrogate models that have not been evaluated as removal attacks. This points to intrinsic flaws in how robustness is currently evaluated. We show that watermarking schemes need to be evaluated against a more extensive set of removal attacks with a more realistic adversary model. Our source code and a complete dataset of evaluation results are publicly available, which allows to independently verify our conclusions.

cs.CR↗

arXiv2019

On the Robustness of the Backdoor-based Watermarking in Deep Neural Networks

Obtaining the state of the art performance of deep learning models imposes a high cost to model generators, due to the tedious data preparation and the substantial processing requirements. To protect the model from unauthorized re-distribution, watermarking approaches have been introduced in the past couple of years. We investigate the robustness and reliability of state-of-the-art deep neural network watermarking schemes. We focus on backdoor-based watermarking and propose two -- a black-box and a white-box -- attacks that remove the watermark. Our black-box attack steals the model and removes the watermark with minimum requirements; it just relies on public unlabeled data and a black-box access to the classification label. It does not need classification confidences or access to the model's sensitive information such as the training data set, the trigger set or the model parameters. The white-box attack, proposes an efficient watermark removal when the parameters of the marked model are available; our white-box attack does not require access to the labeled data or the trigger set and improves the runtime of the black-box attack up to seventeen times. We as well prove the security inadequacy of the backdoor-based watermarking in keeping the watermark undetectable by proposing an attack that detects whether a model contains a watermark. Our attacks show that a recipient of a marked model can remove a backdoor-based watermark with significantly less effort than training a new model and some other techniques are needed to protect against re-distribution by a motivated attacker.

cs.LG↗