Search for: All records

Given the availability of abundant data, deep learning models have been advanced and become ubiquitous in the past decade. In practice, due to many different reasons (e.g., privacy, usability, and fidelity), individuals also want the trained deep models to forget some specific data. Motivated by this, machine unlearning (also known as selective data forgetting) has been intensively studied, which aims at removing the influence that any particular training sample had on the trained model during the unlearning process. However, people usually employ machine unlearning methods as trusted basic tools and rarely have any doubt about their reliability. In fact, the increasingly critical role of machine unlearning makes deep learning models susceptible to the risk of being maliciously attacked. To well understand the performance of deep learning models in malicious environments, we believe that it is critical to study the robustness of deep learning models to malicious unlearning attacks, which happen during the unlearning process. To bridge this gap, in this paper, we first demonstrate that malicious unlearning attacks pose immense threats to the security of deep learning systems. Specifically, we present a broad class of malicious unlearning attacks wherein maliciously crafted unlearning requests trigger deep learning models to misbehave on target samples in a highly controllable and predictable manner. In addition, to improve the robustness of deep learning models, we also present a general defense mechanism, which aims to identify and unlearn effective malicious unlearning requests based on their gradient influence on the unlearned models. Further, theoretical analyses are conducted to analyze the proposed methods. Extensive experiments on real-world datasets validate the vulnerabilities of deep learning models to malicious unlearning attacks and the effectiveness of the introduced defense mechanism. 

Recent progressions in federated learning (FL) have facilitated the development of decentralized collaborative Internet-of-Things (IoT) applications. However, data-driven FL algorithms face the challenge of heterogeneity in participating IoT devices, including their deployment environment and calibration settings. Fail to follow these device-specific properties can degenerate the model performance. To address this issue, we present FedSTL in this poster abstract, which is a two-staged personalized FL framework with clustering for sequential prediction tasks in IoT. FedSTL first identifies client properties as Signal Temporal Logic (STL) specifications. Then, a partitioning component of FedSTL associates each client to an aggregation center, while the framework continues to infer properties for the cluster. At the training stage, both cluster and client models are encouraged to follow customized properties to achieve a hierarchical property enhancing strategy. Further, we show preliminary results of FedSTL in this poster abstract under a synthetic multitask IoT environment and a real-world traffic prediction scenario. 

Physical therapy (PT) is crucial for patients to restore and maintain mobility, function, and well-being. Many on-site activities and body exercises are performed under the supervision of therapists or clinicians. However, the postures of some exercises at home cannot be performed accurately due to the lack of supervision, quality assessment, and self-correction. Therefore, in this paper, we design a new framework, PhysiQ, that continuously tracks and quantitatively measures people's off-site exercise activity through passive sensory detection. In the framework, we create a novel multi-task spatio-temporal Siamese Neural Network that measures the absolute quality through classification and relative quality based on an individual's PT progress through similarity comparison. PhysiQ digitizes and evaluates exercises in three different metrics: range of motions, stability, and repetition. We collect and annotate 31 participants' motion data with different levels of quality. Evaluation results show that PhysiQ recognizes the nuances in exercises, works with different numbers of repetitions, and achieves an accuracy of 89.67% in detecting levels of exercise quality and an average R-squared correlation of 0.949 in similarity comparison. 

As various smart services are increasingly deployed in modern cities, many unexpected conflicts arise due to various physical world couplings. Existing solutions for conflict resolution often rely on centralized control to enforce predetermined and fixed priorities of different services, which is challenging due to the inconsistent and private objectives of the services. Also, the centralized solutions miss opportunities to more effectively resolve conflicts according to their spatiotemporal locality of the conflicts. To address this issue, we design a decentralized negotiation and conflict resolution framework named DeResolver, which allows services to resolve conflicts by communicating and negotiating with each other to reach a Pareto-optimal agreement autonomously and efficiently. Our design features a two-step self-supervised learning-based algorithm to predict acceptable proposals and their rankings of each opponent through the negotiation. Our design is evaluated with a smart city case study of three services: intelligent traffic light control, pedestrian service, and environmental control. In this case study, a data-driven evaluation is conducted using a large dataset consisting of the GPS locations of 246 surveillance cameras and an automatic traffic monitoring system with more than 3 million records per day to extract real-world vehicle routes. The evaluation results show that our solution achieves much more balanced results, i.e., only increasing the average waiting time of vehicles, the measurement metric of intelligent traffic light control service, by 6.8% while reducing the weighted sum of air pollutant emission, measured for environment control service, by 12.1%, and the pedestrian waiting time, the measurement metric of pedestrian service, by 33.1%, compared to priority-based solution. 

Designing effective emergency response management (ERM) systems to respond to incidents such as road accidents is a major problem faced by communities. In addition to responding to frequent incidents each day (about 240 million emergency medical services calls and over 5 million road accidents in the US each year), these systems also support response during natural hazards. Recently, there has been a consistent interest in building decision support and optimization tools that can help emergency responders provide more efficient and effective response. This includes a number of principled subsystems that implement early incident detection, incident likelihood forecasting and strategic resource allocation and dispatch policies. In this paper, we highlight the key challenges and provide an overview of the approach developed by our team in collaboration with our community partners. 

Predictive monitoring—making predictions about future states and monitoring if the predicted states satisfy requirements—offers a promising paradigm in supporting the decision making of Cyber-Physical Systems (CPS). Existing works of predictive monitoring mostly focus on monitoring individual predictions rather than sequential predictions. We develop a novel approach for monitoring sequential predictions generated from Bayesian Recurrent Neural Networks (RNNs) that can capture the inherent uncertainty in CPS, drawing on insights from our study of real-world CPS datasets. We propose a new logic named Signal Temporal Logic with Uncertainty (STL-U) to monitor a flowpipe containing an infinite set of uncertain sequences predicted by Bayesian RNNs. We define STL-U strong and weak satisfaction semantics based on whether all or some sequences contained in a flowpipe satisfy the requirement. We also develop methods to compute the range of confidence levels under which a flowpipe is guaranteed to strongly (weakly) satisfy an STL-U formula. Furthermore, we develop novel criteria that leverage STL-U monitoring results to calibrate the uncertainty estimation in Bayesian RNNs. Finally, we evaluate the proposed approach via experiments with real-world CPS datasets and a simulated smart city case study, which show very encouraging results of STL-U based predictive monitoring approach outperforming baselines. 

Sensing is becoming more and more pervasive. New sensing modalities are enabling the collection of data not previously available. Artificial Intelligence (AI) and cognitive assistance technologies are improving rapidly. Cyber Physical Systems (CPS) are making significant progress in utilizing AI and Machine Learning (ML). This confluence of technologies is giving rise to the potential to achieve the vision of ambient intelligence. This paper describes some of the main challenges and research directions for ambient intelligence from a CPS perspective. Index Terms—Ambient Intelligence, Cyber Physical Systems, Cognitive Assistance, Intelligent Systems