Many machine learning problems can be formulated as consensus optimization problems which can be solved efficiently via a cooperative multi-agent system. However, the agents in the system can be unreliable due to a variety of reasons: noise, faults and attacks. Thus, providing falsified data leads the optimization process in a wrong direction, and degrades the performance of distributed machine learning algorithms. This paper considers the problem of decentralized learning using ADMM in the presence of unreliable agents. First, we rigorously analyze the effect of falsified updates (in ADMM learning iterations) on the convergence behavior of multi-agent system. We show that the algorithm linearly converges to a neighborhood of the optimal solution under certain conditions and characterize the neighborhood size analytically. Next, we provide guidelines for network structure design to achieve a faster convergence. We also provide necessary conditions on the falsified updates for exact convergence to the optimal solution. Finally, to mitigate the influence of unreliable agents, we propose a robust variant of ADMM and show its resilience to unreliable agents.

With the advent of sequential matching (of supply and demand) systems (uber, Lyft, Grab for taxis; ubereats, deliveroo, etc for food; amazon prime, lazada etc. for groceries) across many online and offline services, individuals (taxi drivers, delivery boys, delivery van drivers, etc.) earn more by being at the "right" place at the "right" time. We focus on learning techniques for providing guidance (on right locations to be at right times) to individuals in the presence of other "learning" individuals. Interactions between indivduals are anonymous, i.e, the outcome of an interaction (competing for demand) is independent of the identity of the agents and therefore we refer to these as Anonymous MARL settings. Existing research of relevance is on independent learning using Reinforcement Learning (RL) or on Multi-Agent Reinforcement Learning (MARL). The number of individuals in aggregation systems is extremely large and individuals have their own selfish interest (of maximising revenue). Therefore, traditional MARL approaches are either not scalable or assumptions of common objective or action coordination are not viable. In this paper, we focus on improving performance of independent reinforcement learners, specifically the popular Deep Q-Networks (DQN) and Advantage Actor Critic (A2C) approaches by exploiting anonymity. Specifically, we control non-stationarity introduced by other agents using entropy of agent density distribution. We demonstrate a significant improvement in revenue for individuals and for all agents together with our learners on a generic experimental set up for aggregation systems and a real world taxi dataset.

Operating in a dynamic real world environment requires a forward thinking and adversarial aware design for classifiers, beyond fitting the model to the training data. In such scenarios, it is necessary to make classifiers - a) harder to evade, b) easier to detect changes in the data distribution over time, and c) be able to retrain and recover from model degradation. While most works in the security of machine learning has concentrated on the evasion resistance (a) problem, there is little work in the areas of reacting to attacks (b and c). Additionally, while streaming data research concentrates on the ability to react to changes to the data distribution, they often take an adversarial agnostic view of the security problem. This makes them vulnerable to adversarial activity, which is aimed towards evading the concept drift detection mechanism itself. In this paper, we analyze the security of machine learning, from a dynamic and adversarial aware perspective. The existing techniques of Restrictive one class classifier models, Complex learning models and Randomization based ensembles, are shown to be myopic as they approach security as a static task. These methodologies are ill suited for a dynamic environment, as they leak excessive information to an adversary, who can subsequently launch attacks which are indistinguishable from the benign data. Based on empirical vulnerability analysis against a sophisticated adversary, a novel feature importance hiding approach for classifier design, is proposed. The proposed design ensures that future attacks on classifiers can be detected and recovered from. The proposed work presents motivation, by serving as a blueprint, for future work in the area of Dynamic-Adversarial mining, which combines lessons learned from Streaming data mining, Adversarial learning and Cybersecurity.

Classifiers operating in a dynamic, real world environment, are vulnerable to adversarial activity, which causes the data distribution to change over time. These changes are traditionally referred to as concept drift, and several approaches have been developed in literature to deal with the problem of drift handling and detection. However, most concept drift handling techniques, approach it as a domain independent task, to make them applicable to a wide gamut of reactive systems. These techniques were developed from an adversarial agnostic perspective, where they are naive and assume that drift is a benign change, which can be fixed by updating the model. However, this is not the case when an active adversary is trying to evade the deployed classification system. In such an environment, the properties of concept drift are unique, as the drift is intended to degrade the system and at the same time designed to avoid detection by traditional concept drift detection techniques. This special category of drift is termed as adversarial drift, and this paper analyzes its characteristics and impact, in a streaming environment. A novel framework for dealing with adversarial concept drift is proposed, called the Predict-Detect streaming framework. Experimental evaluation of the framework, on generated adversarial drifting data streams, demonstrates that this framework is able to provide reliable unsupervised indication of drift, and is able to recover from drifts swiftly. While traditional partially labeled concept drift detection methodologies fail to detect adversarial drifts, the proposed framework is able to detect such drifts and operates with <6% labeled data, on average. Also, the framework provides benefits for active learning over imbalanced data streams, by innately providing for feature space honeypots, where minority class adversarial samples may be captured.

We propose and study the problem of generative multi-agent behavioral cloning, where the goal is to learn a generative multi-agent policy from pre-collected demonstration data. Building upon advances in deep generative models, we present a hierarchical policy framework that can tractably learn complex mappings from input states to distributions over multi-agent action spaces. Our framework is flexible and can incorporate high-level domain knowledge into the structure of the underlying deep graphical model. For instance, we can effectively learn low-dimensional structures, such as long-term goals and team coordination, from data. Thus, an additional benefit of our hierarchical approach is the ability to plan over multiple time scales for effective long-term planning. We showcase our approach in an application of modeling team offensive play from basketball tracking data. We show how to instantiate our framework to effectively model complex interactions between basketball players and generate realistic multi-agent trajectories of basketball gameplay over long time periods. We validate our approach using both quantitative and qualitative evaluations, including a user study comparison conducted with professional sports analysts.

Rather than being fearful of machines rising up against humans, one company is actively trying to merge the two, by combining human intelligence with computer algorithms to predict a whole series of real-world events. Unanimous AI is a company that uses technology that draws from a concept commonly found in nature: swarm intelligence. Rather than using algorithms to replace human intelligence, the firm tries to amplify it. "The artificial swarm intelligence really refers to the way in which we actually combine humans with technology in order to come to these amplified outsets, or amplified outcomes," David Baltaxe, chief intelligence officer at Unanimous AI, said on Tuesday. Biologists and zoologists have been studying swarm intelligence in systems of insects and animals, like fishes, birds and honeybees, for a long period of time, Baltaxe told CNBC at the Credit Suisse Asian Investment Conference.

NEW YORK – For a dozen students from Futaba Future High School in Fukushima Prefecture, a recent visit to the United Nations was a chance to share their plans to improve the lives of others by drawing from their catastrophic earthquake and tsunami experiences as a source of strength. Despite overcoming enormous hurdles in the aftermath of the March 11, 2011, disaster that took more than 19,000 lives, the surviving students have moved forward with aspirations of choosing future paths to benefit the global community. "Thanks to all my experiences like getting bullied, joining the drama club and studying at my high school, I think I could grow well," Satsuki Sekine told U.N. diplomats, staff and youth representatives who gathered to hear their presentation on the current situation in Fukushima early this month as part of a scheduled visit while in New York. The 17-year-old explained how drama can be used to portray the challenges of discrimination and conflict "not as an abstract concept but with specific and visual examples." Recounting how the tsunami rendered her home unlivable, she explained how her life in Tomioka as a normal 9-year-old was turned upside down.

Problem domains such as disaster relief, search and rescue, and games can benefit from having a human quickly train coordinated behaviors for a diverse set of agents. Hierarchical Training of Agent Behaviors (HiTAB) is a Learning from Demonstration (LfD) approach that addresses some inherent complexities in multiagent learning, making it possible to train complex heterogeneous behaviors from a small set of training samples. In this paper, we successfully demonstrate LfD training of formation behaviors using a small set of agents that, without retraining, continue to operate correctly when additional agents are available. We selected training of formations for the experiments because formations: require a great deal of coordination between agents, are heterogenous due to the differing roles of participating agents, and can scale as the number of agents grows. We also introduce some extensions to HiTAB that facilitate this type of training.

In our talk we discuss Meta-agents frameworks for working within the Internet of Things (IoT) systems. In particular we discuss our own Meta-agent system called SENtry Agents (SAGE). We discuss why such systems must follow Simon’s laws of the Artificial, and because of that must be Holonic.

We address the question of how to build AI agents that behave ethically by appealing to a computational creativity framework in which output artifacts are agent behaviors and candidate behaviors are evaluated using a normative ethics as the aesthetic measure. We then appeal again to computational creativity to address the meta-level question of which normative ethics the system should employ as its aesthetic, where now output meta-artifacts are normative ethics and candidate ethics are evaluated using a meta-ethics-based aesthetic. We consider briefly some of the issues raised by such a proposal as well as how the hybrid base-meta-level system might be evaluated from three different perspectives: creative, behavioral and ethical.