Xiang‐Yang Li

Yichong Leng, Zehua Chen, Junliang Guo et al. · microsoft-research

Binaural audio plays a significant role in constructing immersive augmented and virtual realities. As it is expensive to record binaural audio from the real world, synthesizing them from mono audio has attracted increasing attention. This synthesis process involves not only the basic physical warping of the mono audio, but also room reverberations and head/ear related filtrations, which, however, are difficult to accurately simulate in traditional digital signal processing. In this paper, we formulate the synthesis process from a different perspective by decomposing the binaural audio into a common part that shared by the left and right channels as well as a specific part that differs in each channel. Accordingly, we propose BinauralGrad, a novel two-stage framework equipped with diffusion models to synthesize them respectively. Specifically, in the first stage, the common information of the binaural audio is generated with a single-channel diffusion model conditioned on the mono audio, based on which the binaural audio is generated by a two-channel diffusion model in the second stage. Combining this novel perspective of two-stage synthesis with advanced generative models (i.e., the diffusion models),the proposed BinauralGrad is able to generate accurate and high-fidelity binaural audio samples. Experiment results show that on a benchmark dataset, BinauralGrad outperforms the existing baselines by a large margin in terms of both object and subject evaluation metrics (Wave L2: 0.128 vs. 0.157, MOS: 3.80 vs. 3.61). The generated audio samples (https://speechresearch.github.io/binauralgrad) and code (https://github.com/microsoft/NeuralSpeech/tree/master/BinauralGrad) are available online.

Jianghao Lin, Xinyi Dai, Yunjia Xi et al.

With the rapid development of online services, recommender systems (RS) have become increasingly indispensable for mitigating information overload. Despite remarkable progress, conventional recommendation models (CRM) still have some limitations, e.g., lacking open-world knowledge, and difficulties in comprehending users' underlying preferences and motivations. Meanwhile, large language models (LLM) have shown impressive general intelligence and human-like capabilities, which mainly stem from their extensive open-world knowledge, reasoning ability, as well as their comprehension of human culture and society. Consequently, the emergence of LLM is inspiring the design of recommender systems and pointing out a promising research direction, i.e., whether we can incorporate LLM and benefit from their knowledge and capabilities to compensate for the limitations of CRM. In this paper, we conduct a comprehensive survey on this research direction from the perspective of the whole pipeline in real-world recommender systems. Specifically, we summarize existing works from two orthogonal aspects: where and how to adapt LLM to RS. For the WHERE question, we discuss the roles that LLM could play in different stages of the recommendation pipeline, i.e., feature engineering, feature encoder, scoring/ranking function, user interaction, and pipeline controller. For the HOW question, we investigate the training and inference strategies, resulting in two fine-grained taxonomy criteria, i.e., whether to tune LLM or not, and whether to involve conventional recommendation models for inference. Then, we highlight key challenges in adapting LLM to RS from three aspects, i.e., efficiency, effectiveness, and ethics. Finally, we summarize the survey and discuss the future prospects. We actively maintain a GitHub repository for papers and other related resources: https://github.com/CHIANGEL/Awesome-LLM-for-RecSys/.

Yichong Leng, Zhifang Guo, Kai Shen et al. · microsoft-research

Speech conveys more information than text, as the same word can be uttered in various voices to convey diverse information. Compared to traditional text-to-speech (TTS) methods relying on speech prompts (reference speech) for voice variability, using text prompts (descriptions) is more user-friendly since speech prompts can be hard to find or may not exist at all. TTS approaches based on the text prompt face two main challenges: 1) the one-to-many problem, where not all details about voice variability can be described in the text prompt, and 2) the limited availability of text prompt datasets, where vendors and large cost of data labeling are required to write text prompts for speech. In this work, we introduce PromptTTS 2 to address these challenges with a variation network to provide variability information of voice not captured by text prompts, and a prompt generation pipeline to utilize the large language models (LLM) to compose high quality text prompts. Specifically, the variation network predicts the representation extracted from the reference speech (which contains full information about voice variability) based on the text prompt representation. For the prompt generation pipeline, it generates text prompts for speech with a speech language understanding model to recognize voice attributes (e.g., gender, speed) from speech and a large language model to formulate text prompts based on the recognition results. Experiments on a large-scale (44K hours) speech dataset demonstrate that compared to the previous works, PromptTTS 2 generates voices more consistent with text prompts and supports the sampling of diverse voice variability, thereby offering users more choices on voice generation. Additionally, the prompt generation pipeline produces high-quality text prompts, eliminating the large labeling cost. The demo page of PromptTTS 2 is available online.

Yichong Leng, Xu Tan, Wenjie Liu et al. · microsoft-research

Error correction in automatic speech recognition (ASR) aims to correct those incorrect words in sentences generated by ASR models. Since recent ASR models usually have low word error rate (WER), to avoid affecting originally correct tokens, error correction models should only modify incorrect words, and therefore detecting incorrect words is important for error correction. Previous works on error correction either implicitly detect error words through target-source attention or CTC (connectionist temporal classification) loss, or explicitly locate specific deletion/substitution/insertion errors. However, implicit error detection does not provide clear signal about which tokens are incorrect and explicit error detection suffers from low detection accuracy. In this paper, we propose SoftCorrect with a soft error detection mechanism to avoid the limitations of both explicit and implicit error detection. Specifically, we first detect whether a token is correct or not through a probability produced by a dedicatedly designed language model, and then design a constrained CTC loss that only duplicates the detected incorrect tokens to let the decoder focus on the correction of error tokens. Compared with implicit error detection with CTC loss, SoftCorrect provides explicit signal about which words are incorrect and thus does not need to duplicate every token but only incorrect tokens; compared with explicit error detection, SoftCorrect does not detect specific deletion/substitution/insertion errors but just leaves it to CTC loss. Experiments on AISHELL-1 and Aidatatang datasets show that SoftCorrect achieves 26.1% and 9.4% CER reduction respectively, outperforming previous works by a large margin, while still enjoying fast speed of parallel generation.

Xiangyang Li, Xiang Long, Yu Xia et al. · pku

Text style transfer (TST) without parallel data has achieved some practical success. However, most of the existing unsupervised text style transfer methods suffer from (i) requiring massive amounts of non-parallel data to guide transferring different text styles. (ii) colossal performance degradation when fine-tuning the model in new domains. In this work, we propose DAML-ATM (Domain Adaptive Meta-Learning with Adversarial Transfer Model), which consists of two parts: DAML and ATM. DAML is a domain adaptive meta-learning approach to learn general knowledge in multiple heterogeneous source domains, capable of adapting to new unseen domains with a small amount of data. Moreover, we propose a new unsupervised TST approach Adversarial Transfer Model (ATM), composed of a sequence-to-sequence pre-trained language model and uses adversarial style training for better content preservation and style transfer. Results on multi-domain datasets demonstrate that our approach generalizes well on unseen low-resource domains, achieving state-of-the-art results against ten strong baselines.

Hui Liu, Weidong Guo, Yige Chen et al. · pku

Headline generation is a task of generating an appropriate headline for a given article, which can be further used for machine-aided writing or enhancing the click-through ratio. Current works only use the article itself in the generation, but have not taken the writing style of headlines into consideration. In this paper, we propose a novel Seq2Seq model called CLH3G (Contrastive Learning enhanced Historical Headlines based Headline Generation) which can use the historical headlines of the articles that the author wrote in the past to improve the headline generation of current articles. By taking historical headlines into account, we can integrate the stylistic features of the author into our model, and generate a headline not only appropriate for the article, but also consistent with the author's style. In order to efficiently learn the stylistic features of the author, we further introduce a contrastive learning based auxiliary task for the encoder of our model. Besides, we propose two methods to use the learned stylistic features to guide both the pointer and the decoder during the generation. Experimental results show that historical headlines of the same user can improve the headline generation significantly, and both the contrastive learning module and the two style features fusion methods can further boost the performance.

Mu Yuan, Lan Zhang, Xiang-Yang Li

Security of model parameters and user data is critical for Transformer-based services, such as ChatGPT. While recent strides in secure two-party protocols have successfully addressed security concerns in serving Transformer models, their adoption is practically infeasible due to the prohibitive cryptographic overheads involved. Drawing insights from our hands-on experience in developing two real-world Transformer-based services, we identify the inherent efficiency bottleneck in the two-party assumption. To overcome this limitation, we propose a novel three-party threat model. Within this framework, we design a semi-symmetric permutation-based protection scheme and present STIP, the first secure Transformer inference protocol without any inference accuracy loss. Experiments on representative Transformer models in real systems show that STIP has practical security and outperforms state-of-the-art secure two-party protocols in efficiency by millions of times.

Mu Yuan, Lan Zhang, Zimu Zheng et al.

The cost efficiency of model inference is critical to real-world machine learning (ML) applications, especially for delay-sensitive tasks and resource-limited devices. A typical dilemma is: in order to provide complex intelligent services (e.g. smart city), we need inference results of multiple ML models, but the cost budget (e.g. GPU memory) is not enough to run all of them. In this work, we study underlying relationships among black-box ML models and propose a novel learning task: model linking, which aims to bridge the knowledge of different black-box models by learning mappings (dubbed model links) between their output spaces. We propose the design of model links which supports linking heterogeneous black-box ML models. Also, in order to address the distribution discrepancy challenge, we present adaptation and aggregation methods of model links. Based on our proposed model links, we developed a scheduling algorithm, named MLink. Through collaborative multi-model inference enabled by model links, MLink can improve the accuracy of obtained inference results under the cost budget. We evaluated MLink on a multi-modal dataset with seven different ML models and two real-world video analytics systems with six ML models and 3,264 hours of video. Experimental results show that our proposed model links can be effectively built among various black-box models. Under the budget of GPU memory, MLink can save 66.7% inference computations while preserving 94% inference accuracy, which outperforms multi-task learning, deep reinforcement learning-based scheduler and frame filtering baselines.

Pengfei Zhou, Yunlong Liu, Junli Liang et al.

Time series forecasting with exogenous variables is a critical emerging paradigm that presents unique challenges in modeling dependencies between variables. Traditional models often struggle to differentiate between endogenous and exogenous variables, leading to inefficiencies and overfitting. In this paper, we introduce CrossLinear, a novel Linear-based forecasting model that addresses these challenges by incorporating a plug-and-play cross-correlation embedding module. This lightweight module captures the dependencies between variables with minimal computational cost and seamlessly integrates into existing neural networks. Specifically, it captures time-invariant and direct variable dependencies while disregarding time-varying or indirect dependencies, thereby mitigating the risk of overfitting in dependency modeling and contributing to consistent performance improvements. Furthermore, CrossLinear employs patch-wise processing and a global linear head to effectively capture both short-term and long-term temporal dependencies, further improving its forecasting precision. Extensive experiments on 12 real-world datasets demonstrate that CrossLinear achieves superior performance in both short-term and long-term forecasting tasks. The ablation study underscores the effectiveness of the cross-correlation embedding module. Additionally, the generalizability of this module makes it a valuable plug-in for various forecasting tasks across different domains. Codes are available at https://github.com/mumiao2000/CrossLinear.

Zihan Wang, Xiangyang Li, Jiahao Yang et al.

Vision-and-language navigation (VLN) enables the agent to navigate to a remote location following the natural language instruction in 3D environments. At each navigation step, the agent selects from possible candidate locations and then makes the move. For better navigation planning, the lookahead exploration strategy aims to effectively evaluate the agent's next action by accurately anticipating the future environment of candidate locations. To this end, some existing works predict RGB images for future environments, while this strategy suffers from image distortion and high computational cost. To address these issues, we propose the pre-trained hierarchical neural radiance representation model (HNR) to produce multi-level semantic features for future environments, which are more robust and efficient than pixel-wise RGB reconstruction. Furthermore, with the predicted future environmental representations, our lookahead VLN model is able to construct the navigable future path tree and select the optimal path via efficient parallel evaluation. Extensive experiments on the VLN-CE datasets confirm the effectiveness of our method.

Ang Li, Qiugen Xiao, Peng Cao et al.

Reinforcement Learning from AI Feedback (RLAIF) has the advantages of shorter annotation cycles and lower costs over Reinforcement Learning from Human Feedback (RLHF), making it highly efficient during the rapid strategy iteration periods of large language model (LLM) training. Using ChatGPT as a labeler to provide feedback on open-domain prompts in RLAIF training, we observe an increase in human evaluators' preference win ratio for model responses, but a decrease in evaluators' satisfaction rate. Analysis suggests that the decrease in satisfaction rate is mainly due to some responses becoming less helpful, particularly in terms of correctness and truthfulness, highlighting practical limitations of basic RLAIF. In this paper, we propose Hybrid Reinforcement Learning from AI Feedback (HRLAIF). This method enhances the accuracy of AI annotations for responses, making the model's helpfulness more robust in training process. Additionally, it employs AI for Red Teaming, further improving the model's harmlessness. Human evaluation results show that HRLAIF inherits the ability of RLAIF to enhance human preference for outcomes at a low cost while also improving the satisfaction rate of responses. Compared to the policy model before Reinforcement Learning (RL), it achieves an increase of 2.08\% in satisfaction rate, effectively addressing the issue of a decrease of 4.58\% in satisfaction rate after basic RLAIF.

Kuicai Dong, Derrick Goh Xin Deik, Yi Quan Lee et al.

Long document question answering (DocQA) aims to answer questions from long documents over 10k words. They usually contain content structures such as sections, sub-sections, and paragraph demarcations. However, the indexing methods of long documents remain under-explored, while existing systems generally employ fixed-length chunking. As they do not consider content structures, the resultant chunks can exclude vital information or include irrelevant content. Motivated by this, we propose the Multi-view Content-aware indexing (MC-indexing) for more effective long DocQA via (i) segment structured document into content chunks, and (ii) represent each content chunk in raw-text, keywords, and summary views. We highlight that MC-indexing requires neither training nor fine-tuning. Having plug-and-play capability, it can be seamlessly integrated with any retrievers to boost their performance. Besides, we propose a long DocQA dataset that includes not only question-answer pair, but also document structure and answer scope. When compared to state-of-art chunking schemes, MC-indexing has significantly increased the recall by 42.8%, 30.0%, 23.9%, and 16.3% via top k= 1.5, 3, 5, and 10 respectively. These improved scores are the average of 8 widely used retrievers (2 sparse and 6 dense) via extensive experiments.

J. Kvapil, G. Borca-Tasciuc, H. Bossi et al.

This R\&D project, initiated by the DOE Nuclear Physics AI-Machine Learning initiative in 2022, leverages AI to address data processing challenges in high-energy nuclear experiments (RHIC, LHC, and future EIC). Our focus is on developing a demonstrator for real-time processing of high-rate data streams from sPHENIX experiment tracking detectors. The limitations of a 15 kHz maximum trigger rate imposed by the calorimeters can be negated by intelligent use of streaming technology in the tracking system. The approach efficiently identifies low momentum rare heavy flavor events in high-rate p+p collisions (3MHz), using Graph Neural Network (GNN) and High Level Synthesis for Machine Learning (hls4ml). Success at sPHENIX promises immediate benefits, minimizing resources and accelerating the heavy-flavor measurements. The approach is transferable to other fields. For the EIC, we develop a DIS-electron tagger using Artificial Intelligence - Machine Learning (AI-ML) algorithms for real-time identification, showcasing the transformative potential of AI and FPGA technologies in high-energy nuclear and particle experiments real-time data processing pipelines.

Haifeng Sun, Yu Xiong, Runze Wu et al.

The burgeoning growth of the esports and multiplayer online gaming community has highlighted the critical importance of evaluating the Most Valuable Player (MVP). The establishment of an explainable and practical MVP evaluation method is very challenging. In our study, we specifically focus on play-by-play data, which records related events during the game, such as assists and points. We aim to address the challenges by introducing a new MVP evaluation framework, denoted as \oursys, which leverages Shapley values. This approach encompasses feature processing, win-loss model training, Shapley value allocation, and MVP ranking determination based on players' contributions. Additionally, we optimize our algorithm to align with expert voting results from the perspective of causality. Finally, we substantiated the efficacy of our method through validation using the NBA dataset and the Dunk City Dynasty dataset and implemented online deployment in the industry.

Haifeng Sun, Yu Xiong, Runze Wu et al.

The value and copyright of training data are crucial in the artificial intelligence industry. Service platforms should protect data providers' legitimate rights and fairly reward them for their contributions. Shapley value, a potent tool for evaluating contributions, outperforms other methods in theory, but its computational overhead escalates exponentially with the number of data providers. Recent works based on Shapley values attempt to mitigate computation complexity by approximation algorithms. However, they need to retrain for each test sample, leading to intolerable costs. We propose Fast-DataShapley, a one-pass training method that leverages the weighted least squares characterization of the Shapley value to train a reusable explainer model with real-time reasoning speed. Given new test samples, no retraining is required to calculate the Shapley values of the training data. Additionally, we propose three methods with theoretical guarantees to reduce training overhead from two aspects: the approximate calculation of the utility function and the group calculation of the training data. We analyze time complexity to show the efficiency of our methods. The experimental evaluations on various image datasets demonstrate superior performance and efficiency compared to baselines. Specifically, the performance is improved to more than 2 times, and the explainer's training speed can be increased by two orders of magnitude.

Fei Shang, Haohua Du, Dawei Yan et al.

Due to its ability to work in non-line-of-sight and low-light environments, radio frequency (RF) imaging technology is expected to bring new possibilities for embodied intelligence and multimodal sensing. However, widely used RF devices (such as Wi-Fi) often struggle to provide high-precision electromagnetic measurements and large-scale datasets, hindering the application of RF imaging technology. In this paper, we combine the ideas of PINN to design the RINN network, using physical constraints instead of true value comparison constraints and adapting it with the characteristics of ubiquitous RF signals, allowing the RINN network to achieve RF imaging using only one sample without phase and with amplitude noise. Our numerical evaluation results show that compared with 5 classic algorithms based on phase data for imaging results, RINN's imaging results based on phaseless data are good, with indicators such as RRMSE (0.11) performing similarly well. RINN provides new possibilities for the universal development of radio frequency imaging technology.

Yuhao Wang, Yichao Wang, Zichuan Fu et al.

As the demand for more personalized recommendation grows and a dramatic boom in commercial scenarios arises, the study on multi-scenario recommendation (MSR) has attracted much attention, which uses the data from all scenarios to simultaneously improve their recommendation performance. However, existing methods tend to integrate insufficient scenario knowledge and neglect learning personalized cross-scenario preferences, thus leading to sub-optimal performance. Meanwhile, though large language model (LLM) has shown great capability of reasoning and capturing semantic information, the high inference latency and high computation cost of tuning hinder its implementation in industrial recommender systems. To fill these gaps, we propose an LLM-enhanced paradigm LLM4MSR in this work. Specifically, we first leverage LLM to uncover multi-level knowledge from the designed scenario- and user-level prompt without fine-tuning the LLM, then adopt hierarchical meta networks to generate multi-level meta layers to explicitly improve the scenario-aware and personalized recommendation capability. Our experiments on KuaiSAR-small, KuaiSAR, and Amazon datasets validate significant advantages of LLM4MSR: (i) the effectiveness and compatibility with different multi-scenario backbone models, (ii) high efficiency and deployability on industrial recommender systems, and (iii) improved interpretability. The implemented code and data is available to ease reproduction.

Tianjian Yang, Hao Zhou, Shuo Liu et al.

The significance of intelligent sensing systems is growing in the realm of smart services. These systems extract relevant signal features and generate informative representations for particular tasks. However, building the feature extraction component for such systems requires extensive domain-specific expertise or data. The exceptionally rapid development of foundation models is likely to usher in newfound abilities in such intelligent sensing. We propose a new scheme for sensing model, which we refer to as semi-generalist sensing model (SGSM). SGSM is able to semiautomatically solve various tasks using relatively less task-specific labeled data compared to traditional systems. Built through the analysis of the common theoretical model, SGSM can depict different modalities, such as the acoustic and Wi-Fi signal. Experimental results on such two heterogeneous sensors illustrate that SGSM functions across a wide range of scenarios, thereby establishing its broad applicability. In some cases, SGSM even achieves better performance than sensor-specific specialized solutions. Wi-Fi evaluations indicate a 20\% accuracy improvement when applying SGSM to an existing sensing model.

Yichong Leng, Xu Tan, Rui Wang et al.

Error correction is widely used in automatic speech recognition (ASR) to post-process the generated sentence, and can further reduce the word error rate (WER). Although multiple candidates are generated by an ASR system through beam search, current error correction approaches can only correct one sentence at a time, failing to leverage the voting effect from multiple candidates to better detect and correct error tokens. In this work, we propose FastCorrect 2, an error correction model that takes multiple ASR candidates as input for better correction accuracy. FastCorrect 2 adopts non-autoregressive generation for fast inference, which consists of an encoder that processes multiple source sentences and a decoder that generates the target sentence in parallel from the adjusted source sentence, where the adjustment is based on the predicted duration of each source token. However, there are some issues when handling multiple source sentences. First, it is non-trivial to leverage the voting effect from multiple source sentences since they usually vary in length. Thus, we propose a novel alignment algorithm to maximize the degree of token alignment among multiple sentences in terms of token and pronunciation similarity. Second, the decoder can only take one adjusted source sentence as input, while there are multiple source sentences. Thus, we develop a candidate predictor to detect the most suitable candidate for the decoder. Experiments on our inhouse dataset and AISHELL-1 show that FastCorrect 2 can further reduce the WER over the previous correction model with single candidate by 3.2% and 2.6%, demonstrating the effectiveness of leveraging multiple candidates in ASR error correction. FastCorrect 2 achieves better performance than the cascaded re-scoring and correction pipeline and can serve as a unified post-processing module for ASR.

Zeqian Ju, Peiling Lu, Xu Tan et al.

Lyric-to-melody generation is an important task in automatic songwriting. Previous lyric-to-melody generation systems usually adopt end-to-end models that directly generate melodies from lyrics, which suffer from several issues: 1) lack of paired lyric-melody training data; 2) lack of control on generated melodies. In this paper, we develop TeleMelody, a two-stage lyric-to-melody generation system with music template (e.g., tonality, chord progression, rhythm pattern, and cadence) to bridge the gap between lyrics and melodies (i.e., the system consists of a lyric-to-template module and a template-to-melody module). TeleMelody has two advantages. First, it is data efficient. The template-to-melody module is trained in a self-supervised way (i.e., the source template is extracted from the target melody) that does not need any lyric-melody paired data. The lyric-to-template module is made up of some rules and a lyric-to-rhythm model, which is trained with paired lyric-rhythm data that is easier to obtain than paired lyric-melody data. Second, it is controllable. The design of template ensures that the generated melodies can be controlled by adjusting the musical elements in template. Both subjective and objective experimental evaluations demonstrate that TeleMelody generates melodies with higher quality, better controllability, and less requirement on paired lyric-melody data than previous generation systems.

Yichong Leng, Xu Tan, Sheng Zhao et al.

Mean opinion score (MOS) is a popular subjective metric to assess the quality of synthesized speech, and usually involves multiple human judges to evaluate each speech utterance. To reduce the labor cost in MOS test, multiple methods have been proposed to automatically predict MOS scores. To our knowledge, for a speech utterance, all previous works only used the average of multiple scores from different judges as the training target and discarded the score of each individual judge, which did not well exploit the precious MOS training data. In this paper, we propose MBNet, a MOS predictor with a mean subnet and a bias subnet to better utilize every judge score in MOS datasets, where the mean subnet is used to predict the mean score of each utterance similar to that in previous works, and the bias subnet to predict the bias score (the difference between the mean score and each individual judge score) and capture the personal preference of individual judges. Experiments show that compared with MOSNet baseline that only leverages mean score for training, MBNet improves the system-level spearmans rank correlation co-efficient (SRCC) by 2.9% on VCC 2018 dataset and 6.7% on VCC 2016 dataset.

Yichong Leng, Xu Tan, Tao Qin et al.

Unsupervised neural machine translation (NMT) has attracted a lot of attention recently. While state-of-the-art methods for unsupervised translation usually perform well between similar languages (e.g., English-German translation), they perform poorly between distant languages, because unsupervised alignment does not work well for distant languages. In this work, we introduce unsupervised pivot translation for distant languages, which translates a language to a distant language through multiple hops, and the unsupervised translation on each hop is relatively easier than the original direct translation. We propose a learning to route (LTR) method to choose the translation path between the source and target languages. LTR is trained on language pairs whose best translation path is available and is applied on the unseen language pairs for path selection. Experiments on 20 languages and 294 distant language pairs demonstrate the advantages of the unsupervised pivot translation for distant languages, as well as the effectiveness of the proposed LTR for path selection. Specifically, in the best case, LTR achieves an improvement of 5.58 BLEU points over the conventional direct unsupervised method.

Yang Fan, Fei Tian, Tao Qin et al.

Teaching plays a very important role in our society, by spreading human knowledge and educating our next generations. A good teacher will select appropriate teaching materials, impact suitable methodologies, and set up targeted examinations, according to the learning behaviors of the students. In the field of artificial intelligence, however, one has not fully explored the role of teaching, and pays most attention to machine \emph{learning}. In this paper, we argue that equal attention, if not more, should be paid to teaching, and furthermore, an optimization framework (instead of heuristics) should be used to obtain good teaching strategies. We call this approach `learning to teach'. In the approach, two intelligent agents interact with each other: a student model (which corresponds to the learner in traditional machine learning algorithms), and a teacher model (which determines the appropriate data, loss function, and hypothesis space to facilitate the training of the student model). The teacher model leverages the feedback from the student model to optimize its own teaching strategies by means of reinforcement learning, so as to achieve teacher-student co-evolution. To demonstrate the practical value of our proposed approach, we take the training of deep neural networks (DNN) as an example, and show that by using the learning to teach techniques, we are able to use much less training data and fewer iterations to achieve almost the same accuracy for different kinds of DNN models (e.g., multi-layer perceptron, convolutional neural networks and recurrent neural networks) under various machine learning tasks (e.g., image classification and text understanding).

Jianwei Qian, Haohua Du, Jiahui Hou et al.

Voice input has been tremendously improving the user experience of mobile devices by freeing our hands from typing on the small screen. Speech recognition is the key technology that powers voice input, and it is usually outsourced to the cloud for the best performance. However, the cloud might compromise users' privacy by identifying their identities by voice, learning their sensitive input content via speech recognition, and then profiling the mobile users based on the content. In this paper, we design an intermediate between users and the cloud, named VoiceMask, to sanitize users' voice data before sending it to the cloud for speech recognition. We analyze the potential privacy risks and aim to protect users' identities and sensitive input content from being disclosed to the cloud. VoiceMask adopts a carefully designed voice conversion mechanism that is resistant to several attacks. Meanwhile, it utilizes an evolution-based keyword substitution technique to sanitize the voice input content. The two sanitization phases are all performed in the resource-limited mobile device while still maintaining the usability and accuracy of the cloud-supported speech recognition service. We implement the voice sanitizer on Android systems and present extensive experimental results that validate the effectiveness and efficiency of our app. It is demonstrated that we are able to reduce the chance of a user's voice being identified from 50 people by 84% while keeping the drop of speech recognition accuracy within 14.2%.

Juanjuan Zhao, Fan Zhang, Lai Tu et al.

Nowadays, metro systems play an important role in meeting the urban transportation demand in large cities. The understanding of passenger route choice is critical for public transit management. The wide deployment of Automated Fare Collection(AFC) systems opens up a new opportunity. However, only each trip's tap-in and tap-out timestamp and stations can be directly obtained from AFC system records; the train and route chosen by a passenger are unknown, which are necessary to solve our problem. While existing methods work well in some specific situations, they don't work for complicated situations. In this paper, we propose a solution that needs no additional equipment or human involvement than the AFC systems. We develop a probabilistic model that can estimate from empirical analysis how the passenger flows are dispatched to different routes and trains. We validate our approach using a large scale data set collected from the Shenzhen metro system. The measured results provide us with useful inputs when building the passenger path choice model.

Lan Zhang, Kebin Liu, Xiang-Yang Li et al.

The wide adoption of wearable smart devices with onboard cameras greatly increases people's concern on privacy infringement. Here we explore the possibility of easing persons from photos captured by smart devices according to their privacy protection requirements. To make this work, we need to address two challenges: 1) how to let users explicitly express their privacy protection intention, and 2) how to associate the privacy requirements with persons in captured photos accurately and efficiently. Furthermore, the association process itself should not cause portrait information leakage and should be accomplished in a privacy-preserving way. In this work, we design, develop, and evaluate a protocol, that enables a user to flexibly express her privacy requirement and empowers the photo service provider (or image taker) to exert the privacy protection policy.Leveraging the visual distinguishability of people in the field-of-view and the dimension-order-independent property of vector similarity measurement, we achieves high accuracy and low overhead. We implement a prototype system, and our evaluation results on both the trace-driven and real-life experiments confirm the feasibility and efficiency of our system.

Cheng Bo, Lan Zhang, Xiang-Yang Li

With the increased popularity of smartphones, various security threats and privacy leakages targeting them are discovered and investigated. In this work, we present \ourprotocoltight, a framework to authenticate users silently and transparently by exploiting dynamics mined from the user touch behavior biometrics and the micro-movement of the device caused by user's screen-touch actions. We build a "touch-based biometrics" model of the owner by extracting some principle features, and then verify whether the current user is the owner or guest/attacker. When using the smartphone, the unique operating dynamics of the user is detected and learnt by collecting the sensor data and touch events silently. When users are mobile, the micro-movement of mobile devices caused by touch is suppressed by that due to the large scale user-movement which will render the touch-based biometrics ineffective. To address this, we integrate a movement-based biometrics for each user with previous touch-based biometrics. We conduct extensive evaluations of our approaches on the Android smartphone, we show that the user identification accuracy is over 99%.

Taeho Jung, Xiang-Yang Li, Lan Zhang

Increasingly more attention is paid to the privacy in online applications due to the widespread data collection for various analysis purposes. Sensitive information might be mined from the raw data during the analysis, and this led to a great privacy concern among people (data providers) these days. To deal with this privacy concerns, multitudes of privacy-preserving computation schemes are proposed to address various computation problems, and we have found many of them fall into a class of problems which can be solved by greedy algorithms. In this paper, we propose a framework for distributed greedy algorithms in which instances in the feasible set come from different parties. By our framework, most generic distributed greedy algorithms can be converted to a privacy preserving one which achieves the same result as the original greedy algorithm while the private information associated with the instances is still protected.

Jizhong Zhao, Wei Xi, Jinsong Han et al.

Generating keys and keeping them secret is critical in secure communications. Due to the "open-air" nature, key distribution is more susceptible to attacks in wireless communications. An ingenious solution is to generate common secret keys by two communicating parties separately without the need of key exchange or distribution, and regenerate them on needs. Recently, it is promising to extract keys by measuring the random variation in wireless channels, e.g., RSS. In this paper, we propose an efficient Secret Key Extraction protocol without Chasing down Errors, SKECE. It establishes common cryptographic keys for two communicating parties in wireless networks via the realtime measurement of Channel State Information (CSI). It outperforms RSS-based approaches for key generation in terms of multiple subcarriers measurement, perfect symmetry in channel, rapid decorrelation with distance, and high sensitivity towards environments. In the SKECE design, we also propose effective mechanisms such as the adaptive key stream generation, leakage resilient consistence validation, and weighted key recombination, to fully exploit the excellent properties of CSI. We implement SKECE on off-the-shelf 802.11n devices and evaluate its performance via extensive experiments. The results demonstrate that SKECE achieves a more than 3x throughput gain in the key generation from one subcarrier in static scenarios, and due to its high efficiency, a 50% reduction on the communication overhead compared to the state-of-the-art RSS based approaches.

Zhiping Jiang, Jizhong Zhao, Xiang-Yang Li et al.

Comparing to well protected data frames, Wi-Fi management frames (MFs) are extremely vulnerable to various attacks. Since MFs are transmitted without encryption, attackers can forge them easily. Such attacks can be detected in cooperative environment such as Wireless Intrusion Detection System (WIDS). However, in non-cooperative environment it is difficult for a single station to identify these spoofing attacks using Received Signal Strength (RSS)-based detection, due to the strong correlation of RSS to both the transmission power (Txpower) and the location of the sender. By exploiting some unique characteristics (i.e., rapid spatial decorrelation, independence of Txpower, and much richer dimensions) of the Channel State Information (CSI), a standard feature in 802.11n Specification, we design a prototype, called CSITE, to authenticate the Wi-Fi management frames by a single station without external support. Our design CSITE, built upon off-the-shelf hardware, achieves precise spoofing detection without collaboration and in-advance finger-print. Several novel techniques are designed to address the challenges caused by user mobility and channel dynamics. To verify the performances of our solution, we implement a prototype of our design and conduct extensive evaluations in various scenarios. Our test results show that our design significantly outperforms the RSS-based method in terms of accuracy, robustness, and efficiency: we observe about 8 times improvement by CSITE over RSS-based method on the falsely accepted attacking frames.

Xiang-Yang Li, Taeho Jung

Location-Based Service (LBS) becomes increasingly popular with the dramatic growth of smartphones and social network services (SNS), and its context-rich functionalities attract considerable users. Many LBS providers use users' location information to offer them convenience and useful functions. However, the LBS could greatly breach personal privacy because location itself contains much information. Hence, preserving location privacy while achieving utility from it is still an challenging question now. This paper tackles this non-trivial challenge by designing a suite of novel fine-grained Privacy-preserving Location Query Protocol (PLQP). Our protocol allows different levels of location query on encrypted location information for different users, and it is efficient enough to be applied in mobile platforms.

Lan Zhang, Xiang-Yang Li

Many proximity-based mobile social networks are developed to facilitate connections between any two people, or to help a user to find people with matched profile within a certain distance. A challenging task in these applications is to protect the privacy the participants' profiles and personal interests. In this paper, we design novel mechanisms, when given a preference-profile submitted by a user, that search a person with matching-profile in decentralized multi-hop mobile social networks. Our mechanisms are privacy-preserving: no participants' profile and the submitted preference-profile are exposed. Our mechanisms establish a secure communication channel between the initiator and matching users at the time when the matching user is found. Our rigorous analysis shows that our mechanism is secure, privacy-preserving, verifiable, and efficient both in communication and computation. Extensive evaluations using real social network data, and actual system implementation on smart phones show that our mechanisms are significantly more efficient then existing solutions.

Taeho Jung, XuFei Mao, Xiang-Yang Li et al.

Much research has been conducted to securely outsource multiple parties' data aggregation to an untrusted aggregator without disclosing each individual's data, or to enable multiple parties to jointly aggregate their data while preserving privacy. However, those works either assume to have a secure channel or suffer from high complexity. Here we consider how an external aggregator or multiple parties learn some algebraic statistics (e.g., summation, product) over participants' data while any individual's input data is kept secret to others (the aggregator and other participants). We assume channels in our construction are insecure. That is, all channels are subject to eavesdropping attacks, and all the communications throughout the aggregation are open to others. We successfully guarantee data confidentiality under this weak assumption while limiting both the communication and computation complexity to at most linear.

Taeho Jung, Xiang-Yang Li, Zhiguo Wan et al.

Cloud computing is a revolutionary computing paradigm which enables flexible, on-demand and low-cost usage of computing resources. However, those advantages, ironically, are the causes of security and privacy problems, which emerge because the data owned by different users are stored in some cloud servers instead of under their own control. To deal with security problems, various schemes based on the Attribute- Based Encryption (ABE) have been proposed recently. However, the privacy problem of cloud computing is yet to be solved. This paper presents an anonymous privilege control scheme AnonyControl to address the user and data privacy problem in a cloud. By using multiple authorities in cloud computing system, our proposed scheme achieves anonymous cloud data access, finegrained privilege control, and more importantly, tolerance to up to (N -2) authority compromise. Our security and performance analysis show that AnonyControl is both secure and efficient for cloud computing environment.