Lifelong learning algorithms enable models to incrementally acquire new knowledge without forgetting previously learned information. Contrarily, the field of machine unlearning focuses on explicitly forgetting certain previous knowledge from pretrained models when requested, in order to comply with data privacy regulations on the right-to-be-forgotten. Enabling efficient lifelong learning with the capability to selectively unlearn sensitive information from models presents a critical and largely unaddressed challenge with contradicting objectives. We address this problem from the perspective of simultaneously preventing catastrophic forgetting and allowing forward knowledge transfer during task-incremental learning, while ensuring exact task unlearning and minimizing memory requirements, based on a single neural network model to be adapted. Our proposed solution, privacy-aware lifelong learning (PALL), involves optimization of task-specific sparse subnetworks with parameter sharing within a single architecture. We additionally utilize an episodic memory rehearsal mechanism to facilitate exact unlearning without performance degradations. We empirically demonstrate the scalability of PALL across various architectures in image classification, and provide a state-of-the-art solution that uniquely integrates lifelong learning and privacy-aware unlearning mechanisms for responsible AI applications.
University of Pennsylvania（宾夕法尼亚大学）；HRL Laboratories, LLC（HRL实验室有限责任公司）
Lifelong machine learning methods acquire knowledge over a series of consecutive tasks, continually building upon their experience. Current lifelong learning algorithms rely upon a single learning agent that has centralized access to all data. In this paper, we extend the idea of lifelong learning from a single agent to a network of multiple agents that collectively learn a series of tasks. Each agent faces some (potentially unique) set of tasks; the key idea is that knowledge learned from these tasks may benefit other agents trying to learn different (but related) tasks. Our Collective Lifelo…
Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；École Polytechnique de Montréal（蒙特利尔综合理工大学）；Robert Bosch Center for Data Science and Artificial Intelligence（罗伯特·博世数据科学与人工智能中心）；IIT Madras（印度理工学院马德拉斯分校）
When an agent encounters a continual stream of new tasks in the lifelong learning setting, it leverages the knowledge it gained from the earlier tasks to help learn the new tasks better. In such a scenario, identifying an efficient knowledge representation becomes a challenging problem. Most research works propose to either store a subset of examples from the past tasks in a replay buffer, dedicate a separate set of parameters to each task or penalize excessive updates over parameters by introducing a regularization term. While existing methods employ the general task-agnostic stochastic gradi…
Advanced Research Lab, NavInfo Europe（四维图新欧洲先进研究实验室）；Eindhoven University of Technology（埃因霍温理工大学）
Intelligent systems deployed in the real world suffer from catastrophic forgetting when exposed to a sequence of tasks. Humans, on the other hand, acquire, consolidate, and transfer knowledge between tasks that rarely interfere with the consolidated knowledge. Accompanied by self-regulated neurogenesis, continual learning in the brain is governed by a rich set of neurophysiological processes that harbor different types of knowledge, which are then integrated by conscious processing. Thus, inspired by the Global Workspace Theory of conscious information access in the brain, we propose TAMiL, a …
Kent State University（肯特州立大学）；University of Florida（佛罗里达大学）；Qualcomm Incorporated（高通公司）
In this paper, we show that the process of continually learning new tasks and memorizing previous tasks introduces unknown privacy risks and challenges to bound the privacy loss. Based upon this, we introduce a formal definition of Lifelong DP, in which the participation of any data tuples in the training set of any tasks is protected, under a consistently bounded DP protection, given a growing stream of tasks. A consistently bounded DP means having only one fixed value of the DP privacy budget, regardless of the number of tasks. To preserve Lifelong DP, we propose a scalable and heterogeneous…
Task-Aware Multi-Expert Architecture For Lifelong Deep Learning
Dept. of Computational and Data Sciences George Mason University Fairfax VA USA（计算与数据科学系，乔治·马歇尔大学）；Dept. of Computer Science George Mason University Fairfax VA USA（计算机科学系，乔治·马歇尔大学）；Dept. of Electrical and Computer Engineering Duke University Durham NC USA（电气与计算机工程系，达特茅斯大学）
Bigabid Inc.（Bigabid公司）；Ben-Gurion University of the Negev（内盖夫本-古里安大学）
Over the past decade, programmatic advertising has received a great deal of attention in the online advertising industry. A real-time bidding (RTB) system is rapidly becoming the most popular method to buy and sell online advertising impressions. Within the RTB system, demand-side platforms (DSP) aim to spend advertisers' campaign budgets efficiently while maximizing profit, seeking impressions that result in high user responses, such as clicks or installs. In the current study, we investigate the process of predicting a mobile gaming app installation from the point of view of a particular DSP…
AriadneMem: Threading the Maze of Lifelong Memory for LLM Agents
Arizona State University（亚利桑那州立大学）；Morgan Stanley（摩根大通）；Rice University（里奇大学）；Clemson University（克莱姆森大学）；Northwestern University（西北大学）；UC Davis（加州大学戴维斯分校）；Iowa State University（爱荷华州立大学）；Washington University in St. Louis（圣路易斯华盛顿大学）；Columbia University（哥伦比亚大学）；Halmstad University（哈马格大学）
Federated data analytics is a framework for distributed data analysis where a server compiles noisy responses from a group of distributed low-bandwidth user devices to estimate aggregate statistics. Two major challenges in this framework are privacy, since user data is often sensitive, and compression, since the user devices have low network bandwidth. Prior work has addressed these challenges separately by combining standard compression algorithms with known privacy mechanisms. In this work, we take a holistic look at the problem and design a family of privacy-aware compression mechanisms tha…
Department of Industrial and Systems Engineering, Texas A&M University（工业与系统工程系，德克萨斯A&M大学）；Department of Aerospace Engineering, Texas A&M University（航空航天工程系，德克萨斯A&M大学）
In this paper, we design Top-DP, a novel solution to optimize the differential privacy protection of decentralized image classification systems. The key insight of our solution is to leverage the unique features of decentralized communication topologies to reduce the noise scale and improve the model usability. (1) We enhance the DP-SGD algorithm with this topology-aware noise reduction strategy, and integrate the time-aware noise decay technique. (2) We design two novel learning protocols (synchronous and asynchronous) to protect systems with different network connectivities and topologies. W…
Cornell University（康奈尔大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）
Local differential privacy (LDP) can be adopted to anonymize richer user data attributes that will be input to sophisticated machine learning (ML) tasks. However, today's LDP approaches are largely task-agnostic and often lead to severe performance loss -- they simply inject noise to all data attributes according to a given privacy budget, regardless of what features are most relevant for the ultimate task. In this paper, we address how to significantly improve the ultimate task performance with multi-dimensional user data by considering a task-aware privacy preservation problem. The key idea …
The remarkable ability of language models (LMs) has also brought challenges at the interface of AI and security. A critical challenge pertains to how much information these models retain and leak about the training data. This is particularly urgent as the typical development of LMs relies on huge, often highly sensitive data, such as emails and chat logs. To contrast this shortcoming, this paper introduces Context-Aware Differentially Private Language Model (CADP-LM) , a privacy-preserving LM framework that relies on two key insights: First, it utilizes the notion of \emph{context} to define a…
University of Texas (UT) at Austin（德克萨斯大学奥斯汀分校）；University of Sao Paulo (USP)（圣保罗大学）
This paper introduces a privacy-aware Bayesian approach that combines ensembles of classifiers and clusterers to perform semi-supervised and transductive learning. We consider scenarios where instances and their classification/clustering results are distributed across different data sites and have sharing restrictions. As a special case, the privacy aware computation of the model when instances of the target data are distributed across different data sites, is also discussed. Experimental results show that the proposed approach can provide good classification accuracies while adhering to the d…
PWC-MoE: Privacy-Aware Wireless Collaborative Mixture of Experts
Department of Engineering, King’s College London（伦敦国王学院工程系）；Institute for Digital Communication, Friedrich-Alexander-Universität Erlangen-Nürnberg（埃朗根-纽伦堡弗里德里希-亚历山大大学数字通信研究所）
Purdue University（普渡大学）；Penn State University（宾夕法尼亚州立大学）
Users trust IoT apps to control and automate their smart devices. These apps necessarily have access to sensitive data to implement their functionality. However, users lack visibility into how their sensitive data is used (or leaked), and they often blindly trust the app developers. In this paper, we present IoTWatcH, a novel dynamic analysis tool that uncovers the privacy risks of IoT apps in real-time. We designed and built IoTWatcH based on an IoT privacy survey that considers the privacy needs of IoT users. IoTWatcH provides users with a simple interface to specify their privacy preference…
University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of Florida（佛罗里达大学）
Kickstarting deep reinforcement learning algorithms facilitate a teacher-student relationship among the agents and allow for a well-performing teacher to share demonstrations with a student to expedite the student's training. However, despite the known benefits, the demonstrations may contain sensitive information about the teacher's training data and existing kickstarting methods do not take any measures to protect it. Therefore, we use the framework of differential privacy to develop a mechanism that securely shares the teacher's demonstrations with the student. The mechanism allows for the …
We study statistical risk minimization problems under a privacy model in which the data is kept confidential even from the learner. In this local privacy framework, we establish sharp upper and lower bounds on the convergence rates of statistical estimation procedures. As a consequence, we exhibit a precise tradeoff between the amount of privacy the data preserves and the utility, as measured by convergence rate, of any statistical estimator or learning procedure.
Reinforcement learning (RL) presents numerous benefits compared to rule-based approaches in various applications. Privacy concerns have grown with the widespread use of RL trained with privacy-sensitive data in IoT devices, especially for human-in-the-loop systems. On the one hand, RL methods enhance the user experience by trying to adapt to the highly dynamic nature of humans. On the other hand, trained policies can leak the user's private information. Recent attention has been drawn to designing privacy-aware RL algorithms while maintaining an acceptable system utility. A central challenge i…
Privacy-Aware Video Anomaly Detection through Orthogonal Subspace Projection
School of Engineering and Built Environment, Griffith University（格里菲斯大学工程与环境学院）；School of Computer Science and Engineering, University of New South Wales（新南威尔士大学计算机科学与工程学院）；School of Information and Communication Technology, Griffith University（格里菲斯大学信息与通信技术学院）
In the big data era, more and more cloud-based data-driven applications are developed that leverage individual data to provide certain valuable services (the utilities). On the other hand, since the same set of individual data could be utilized to infer the individual's certain sensitive information, it creates new channels to snoop the individual's privacy. Hence it is of great importance to develop techniques that enable the data owners to release privatized data, that can still be utilized for certain premised intended purpose. Existing data releasing approaches, however, are either privacy…
In this paper, localized information privacy (LIP) is proposed, as a new privacy definition, which allows statistical aggregation while protecting users' privacy without relying on a trusted third party. The notion of context-awareness is incorporated in LIP by the introduction of priors, which enables the design of privacy-preserving data aggregation with knowledge of priors. We show that LIP relaxes the Localized Differential Privacy (LDP) notion by explicitly modeling the adversary's knowledge. However, it is stricter than $2ε$-LDP and $ε$-mutual information privacy. The incorporation of lo…
Local differential privacy (LDP) is a strong notion of privacy for individual users that often comes at the expense of a significant drop in utility. The classical definition of LDP assumes that all elements in the data domain are equally sensitive. However, in many applications, some symbols are more sensitive than others. This work proposes a context-aware framework of local differential privacy that allows a privacy designer to incorporate the application's context into the privacy definition. For binary data domains, we provide a universally optimal privatization scheme and highlight its c…
Arizona State University（亚利桑那州立大学）；Stanford University（斯坦福大学）
Preserving the utility of published datasets while simultaneously providing provable privacy guarantees is a well-known challenge. On the one hand, context-free privacy solutions, such as differential privacy, provide strong privacy guarantees, but often lead to a significant reduction in utility. On the other hand, context-aware privacy solutions, such as information theoretic privacy, achieve an improved privacy-utility tradeoff, but assume that the data holder has access to dataset statistics. We circumvent these limitations by introducing a novel context-aware privacy framework called gene…
A Neighbourhood-Aware Differential Privacy Mechanism for Static Word Embeddings
University of Liverpool（利物浦大学）；Amazon（亚马逊）；National Institute of Informatics（国立信息学研究所）；International Professional University of Technology in Tokyo（东京国际工科专门职大学）
Henley Business School, University of Reading（雷丁大学亨利商学院）；University of Thessaly（色萨利大学）
The extensive use of online social media has highlighted the importance of privacy in the digital space. As more scientists analyse the data created in these platforms, privacy concerns have extended to data usage within the academia. Although text analysis is a well documented topic in academic literature with a multitude of applications, ensuring privacy of user-generated content has been overlooked. Most sentiment analysis methods require emotion labels, which can be obtained through crowdsourcing, where non-expert individuals contribute to scientific tasks. The text itself has to be expose…
Ghent University - imec（根特大学 - imec）；Ghent University（根特大学）
Deep neural networks require large amounts of resources which makes them hard to use on resource constrained devices such as Internet-of-things devices. Offloading the computations to the cloud can circumvent these constraints but introduces a privacy risk since the operator of the cloud is not necessarily trustworthy. We propose a technique that obfuscates the data before sending it to the remote computation node. The obfuscated data is unintelligible for a human eavesdropper but can still be classified with a high accuracy by a neural network trained on unobfuscated images.
