Government
Machine learning and the Search for E.T.
If there is life beyond Earth, it's going to be found on an exoplanet--planets orbiting stars other than our own sun. The number of exoplanets is thought to number in the trillions [1], but despite an abundance of data from exoplanet-finding missions like Kepler, K2, and TESS, just a few thousands of potential exoplanets have been confirmed. The biggest problem is a glut of information; About 30 GB is being collected every day from NASA's Transiting Exoplanet Survey Satellite (TESS) mission [2], which launched in 2018. This gives astronomers an overwhelming amount of data to analyze. In addition, the sheer number of candidate stars, which stretches into the millions, confounds the problem and results in too many candidate exoplanets to manage without the assistance of ML.
RADAMS: Resilient and Adaptive Alert and Attention Management Strategy against Informational Denial-of-Service (IDoS) Attacks
Attacks exploiting human attentional vulnerability have posed severe threats to cybersecurity. In this work, we identify and formally define a new type of proactive attentional attacks called Informational Denial-of-Service (IDoS) attacks that generate a large volume of feint attacks to overload human operators and hide real attacks among feints. We incorporate human factors (e.g., levels of expertise, stress, and efficiency) and empirical results (e.g., the Yerkes-Dodson law and the sunk cost fallacy) to model the operators' attention dynamics and their decision-making processes along with the real-time alert monitoring and inspection. To assist human operators in timely and accurately dismissing the feints and escalating the real attacks, we develop a Resilient and Adaptive Data-driven alert and Attention Management Strategy (RADAMS) that de-emphasizes alerts selectively based on the alerts' observable features. RADAMS uses reinforcement learning to achieve a customized and transferable design for various human operators and evolving IDoS attacks. The integrated modeling and theoretical analysis lead to the Product Principle of Attention (PPoA), fundamental limits, and the tradeoff among crucial human and economic factors. Experimental results corroborate that the proposed strategy outperforms the default strategy and can reduce the IDoS risk by as much as 20%. Besides, the strategy is resilient to large variations of costs, attack frequencies, and human attention capacities. We have recognized interesting phenomena such as attentional risk equivalency, attacker's dilemma, and the half-truth optimal attack strategy.
Mixture Proportion Estimation and PU Learning: A Modern Approach
Garg, Saurabh, Wu, Yifan, Smola, Alex, Balakrishnan, Sivaraman, Lipton, Zachary C.
Given only positive examples and unlabeled examples (from both positive and negative classes), we might hope nevertheless to estimate an accurate positive-versus-negative classifier. Formally, this task is broken down into two subtasks: (i) Mixture Proportion Estimation (MPE) -- determining the fraction of positive examples in the unlabeled data; and (ii) PU-learning -- given such an estimate, learning the desired positive-versus-negative classifier. Unfortunately, classical methods for both problems break down in high-dimensional settings. Meanwhile, recently proposed heuristics lack theoretical coherence and depend precariously on hyperparameter tuning. In this paper, we propose two simple techniques: Best Bin Estimation (BBE) (for MPE); and Conditional Value Ignoring Risk (CVIR), a simple objective for PU-learning. Both methods dominate previous approaches empirically, and for BBE, we establish formal guarantees that hold whenever we can train a model to cleanly separate out a small subset of positive examples. Our final algorithm (TED)$^n$, alternates between the two procedures, significantly improving both our mixture proportion estimator and classifier
On the Current and Emerging Challenges of Developing Fair and Ethical AI Solutions in Financial Services
Kurshan, Eren, Chen, Jiahao, Storchan, Victor, Shen, Hongda
Artificial intelligence (AI) continues to find more numerous and more critical applications in the financial services industry, giving rise to fair and ethical AI as an industry-wide objective. While many ethical principles and guidelines have been published in recent years, they fall short of addressing the serious challenges that model developers face when building ethical AI solutions. We survey the practical and overarching issues surrounding model development, from design and implementation complexities, to the shortage of tools, and the lack of organizational constructs. We show how practical considerations reveal the gaps between high-level principles and concrete, deployed AI applications, with the aim of starting industry-wide conversations toward solution approaches.
Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey
Min, Bonan, Ross, Hayley, Sulem, Elior, Veyseh, Amir Pouran Ben, Nguyen, Thien Huu, Sainz, Oscar, Agirre, Eneko, Heinz, Ilana, Roth, Dan
Large, pre-trained transformer-based language models such as BERT have drastically changed the Natural Language Processing (NLP) field. We present a survey of recent work that uses these large language models to solve NLP tasks via pre-training then fine-tuning, prompting, or text generation approaches. We also present approaches that use pre-trained language models to generate data for training augmentation or other purposes. We conclude with discussions on limitations and suggested directions for future research.
Low-Cost Algorithmic Recourse for Users With Uncertain Cost Functions
Yadav, Prateek, Hase, Peter, Bansal, Mohit
The problem of identifying algorithmic recourse for people affected by machine learning model decisions has received much attention recently. Some recent works model user-incurred cost, which is directly linked to user satisfaction. But they assume a single global cost function that is shared across all users. This is an unrealistic assumption when users have dissimilar preferences about their willingness to act upon a feature and different costs associated with changing that feature. In this work, we formalize the notion of user-specific cost functions and introduce a new method for identifying actionable recourses for users. By default, we assume that users' cost functions are hidden from the recourse method, though our framework allows users to partially or completely specify their preferences or cost function. We propose an objective function, Expected Minimum Cost (EMC), based on two key ideas: (1) when presenting a set of options to a user, it is vital that there is at least one low-cost solution the user could adopt; (2) when we do not know the user's true cost function, we can approximately optimize for user satisfaction by first sampling plausible cost functions, then finding a set that achieves a good cost for the user in expectation. We optimize EMC with a novel discrete optimization algorithm, Cost-Optimized Local Search (COLS), which is guaranteed to improve the recourse set quality over iterations. Experimental evaluation on popular real-world datasets with simulated user costs demonstrates that our method satisfies up to 25.89 percentage points more users compared to strong baseline methods. Using standard fairness metrics, we also show that our method can provide more fair solutions across demographic groups than comparable methods, and we verify that our method is robust to misspecification of the cost function distribution.
Stakeholder Participation in AI: Beyond "Add Diverse Stakeholders and Stir"
Delgado, Fernando, Yang, Stephen, Madaio, Michael, Yang, Qian
There is a growing consensus in HCI and AI research that the design of AI systems needs to engage and empower stakeholders who will be affected by AI. However, the manner in which stakeholders should participate in AI design is unclear. This workshop paper aims to ground what we dub a 'participatory turn' in AI design by synthesizing existing literature on participation and through empirical analysis of its current practices via a survey of recent published research and a dozen semi-structured interviews with AI researchers and practitioners. Based on our literature synthesis and empirical research, this paper presents a conceptual framework for analyzing participatory approaches to AI design and articulates a set of empirical findings that in ensemble detail out the contemporary landscape of participatory practice in AI design. These findings can help bootstrap a more principled discussion on how PD of AI should move forward across AI, HCI, and other research communities.
AI Regulation: The EU should not give in to the surveillance industry lobbies
Although it claims to protect our liberties, the EU's draft text on artificial intelligence (AI), presented by Margrethe Vestager, actually promotes the accelerated development of all aspects of AI, in particular for security purposes. Loaded with exceptions, resting on a stale risk-based approach, and picking up the French government's rhetoric on the need for more experimentation, this text should be modified down to its foundation. In its current state it risks endangering the slim legal protections that European law holds out in face of the massive deployment of surveillance techniques in public space. On April 21, 2021 the European Commission (EC) published a regulation proposal for a "European approach" to AI, accompanied by a coordinating plan to guide member states' action for the years to come. Beyond the rethoric of the European Commission, the draft regulation is deeply insufficient in how it treats the danger that AI systems represent for fundamental freedoms.