arXiv subjects

Shaofeng Li

Publications and source records attributed to Shaofeng Li.

25 records · Page 2Linked to original sources

arXiv2023

Digital Twin-Assisted Adaptive Preloading for Short Video Streaming

We propose a digital twin-assisted adaptive preloading scheme to enhance bandwidth efficiency and user quality of experience (QoE) in short video streaming. We first analyze the relationship between the achievable throughput and video bitrate and critical factors that affect the preloading decision, including the buffer size and bitrate selection. We then construct a digital twin-assisted adaptive preloading framework for short video streaming. By collecting and analyzing historical throughput and tracking behavior information, a throughput prediction model and a probabilistic model can be constructed to accurately predict future throughput and user behavior, respectively. Using the predicted information and real-time running status data from a short video application, we design a preloading strategy to enhance bandwidth efficiency while guaranteeing user QoE. Simulation results demonstrate the effectiveness of our proposed scheme comparing with the state-of-the-art preloading schemes.

cs.NI↗

arXiv2023

Split Federated Learning: Speed up Model Training in Resource-Limited Wireless Networks

In this paper, we propose a novel distributed learning scheme, named group-based split federated learning (GSFL), to speed up artificial intelligence (AI) model training. Specifically, the GSFL operates in a split-then-federated manner, which consists of three steps: 1) Model distribution, in which the access point (AP) splits the AI models and distributes the client-side models to clients; 2) Model training, in which each client executes forward propagation and transmit the smashed data to the edge server. The edge server executes forward and backward propagation and then returns the gradient to the clients for updating local client-side models; and 3) Model aggregation, in which edge servers aggregate the server-side and client-side models. Simulation results show that the GSFL outperforms vanilla split learning and federated learning schemes in terms of overall training latency while achieving satisfactory accuracy.

cs.DC↗

arXiv2022

Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations

In this paper, we propose a novel and practical mechanism which enables the service provider to verify whether a suspect model is stolen from the victim model via model extraction attacks. Our key insight is that the profile of a DNN model's decision boundary can be uniquely characterized by its Universal Adversarial Perturbations (UAPs). UAPs belong to a low-dimensional subspace and piracy models' subspaces are more consistent with victim model's subspace compared with non-piracy model. Based on this, we propose a UAP fingerprinting method for DNN models and train an encoder via contrastive learning that takes fingerprint as inputs, outputs a similarity score. Extensive studies show that our framework can detect model IP breaches with confidence > 99.99 within only 20 fingerprints of the suspect model. It has good generalizability across different model architectures and is robust against post-modifications on stolen models.

cs.CR↗

arXiv2021

Hidden Backdoors in Human-Centric Language Models

Natural language processing (NLP) systems have been proven to be vulnerable to backdoor attacks, whereby hidden features (backdoors) are trained into a language model and may only be activated by specific inputs (called triggers), to trick the model into producing unexpected behaviors. In this paper, we create covert and natural triggers for textual backdoor attacks, \textit{hidden backdoors}, where triggers can fool both modern language models and human inspection. We deploy our hidden backdoors through two state-of-the-art trigger embedding methods. The first approach via homograph replacement, embeds the trigger into deep neural networks through the visual spoofing of lookalike character replacement. The second approach uses subtle differences between text generated by language models and real natural text to produce trigger sentences with correct grammar and high fluency. We demonstrate that the proposed hidden backdoors can be effective across three downstream security-critical NLP tasks, representative of modern human-centric NLP systems, including toxic comment detection, neural machine translation (NMT), and question answering (QA). Our two hidden backdoor attacks can achieve an Attack Success Rate (ASR) of at least $97\%$ with an injection rate of only $3\%$ in toxic comment detection, $95.1\%$ ASR in NMT with less than $0.5\%$ injected data, and finally $91.12\%$ ASR against QA updated with only 27 poisoning data samples on a model previously trained with 92,024 samples (0.029\%). We are able to demonstrate the adversary's high success rate of attacks, while maintaining functionality for regular users, with triggers inconspicuous by the human administrators.

cs.CL↗

arXiv2021

Deep Learning Backdoors

Intuitively, a backdoor attack against Deep Neural Networks (DNNs) is to inject hidden malicious behaviors into DNNs such that the backdoor model behaves legitimately for benign inputs, yet invokes a predefined malicious behavior when its input contains a malicious trigger. The trigger can take a plethora of forms, including a special object present in the image (e.g., a yellow pad), a shape filled with custom textures (e.g., logos with particular colors) or even image-wide stylizations with special filters (e.g., images altered by Nashville or Gotham filters). These filters can be applied to the original image by replacing or perturbing a set of image pixels.

cs.CR↗

arXiv2020

Invisible Backdoor Attacks on Deep Neural Networks via Steganography and Regularization

Deep neural networks (DNNs) have been proven vulnerable to backdoor attacks, where hidden features (patterns) trained to a normal model, which is only activated by some specific input (called triggers), trick the model into producing unexpected behavior. In this paper, we create covert and scattered triggers for backdoor attacks, invisible backdoors, where triggers can fool both DNN models and human inspection. We apply our invisible backdoors through two state-of-the-art methods of embedding triggers for backdoor attacks. The first approach on Badnets embeds the trigger into DNNs through steganography. The second approach of a trojan attack uses two types of additional regularization terms to generate the triggers with irregular shape and size. We use the Attack Success Rate and Functionality to measure the performance of our attacks. We introduce two novel definitions of invisibility for human perception; one is conceptualized by the Perceptual Adversarial Similarity Score (PASS) and the other is Learned Perceptual Image Patch Similarity (LPIPS). We show that the proposed invisible backdoors can be fairly effective across various DNN models as well as four datasets MNIST, CIFAR-10, CIFAR-100, and GTSRB, by measuring their attack success rates for the adversary, functionality for the normal users, and invisibility scores for the administrators. We finally argue that the proposed invisible backdoor attacks can effectively thwart the state-of-the-art trojan backdoor detection approaches, such as Neural Cleanse and TABOR.

cs.CR↗

arXiv2015

Higgs boson production and decay at $e^{+}e^{-}$ colliders as a probe of the Left-Right twin Higgs model

In the framework of the Left-Right twin Higgs (LRTH) model, we consider the constrains from the latest search for high-mass dilepton resonances at the LHC and find that the heavy neutral boson $Z_H$ is excluded with mass below 2.76 TeV. Under these constrains, we study the Higgs-Gauge coupling production processes $e^{+}e^{-}\rightarrow ZH$, $e^{+}e^{-}\rightarrow ν_{e}\bar{ν_{e}}H$ and $e^{+}e^{-}\rightarrow e^{+}e^{-}H$, top quark Yukawa coupling production process $e^{+}e^{-}\rightarrow t\bar{t}H$, Higgs self-couplings production processes $e^{+}e^{-}\rightarrow ZHH$ and $e^{+}e^{-}\rightarrow ν_{e}\bar{ν_{e}}HH$ at $e^{+}e^{-}$ colliders. Besides, we study the major decay modes of the Higgs boson, namely $h\rightarrow f\bar{f}$($f=b,c,τ$), $VV^{*}(V=W, Z)$, $gg$, $γγ$. We find that the LRTH effects are sizable so that the Higgs boson processes at $e^{+}e^{-}$ collider can be a sensitive probe for the LRTH model.

hep-ph↗