Related papers: Attack RMSE Leaderboard: An Introduction and Case …
Models that top leaderboards often perform unsatisfactorily when deployed in real world applications; this has necessitated rigorous and expensive pre-deployment model testing. A hitherto unexplored facet of model performance is: Are our…
In recent years, Reward Machines (RMs) have stood out as a simple yet effective automata-based formalism for exposing and exploiting task structure in reinforcement learning settings. Despite their relevance, little to no attention has been…
While poisoning attacks on machine learning models have been extensively studied, the mechanisms by which adversaries can distribute poisoned models at scale remain largely unexplored. In this paper, we shed light on how model leaderboards…
Membership inference attacks are designed to determine, using black box access to trained models, whether a particular example was used in training or not. Membership inference can be formalized as a hypothesis testing problem. The most…
While machine learning is vulnerable to adversarial examples, it still lacks systematic procedures and tools for evaluating its security in different application contexts. In this article, we discuss how to develop automated and scalable…
Membership inference attacks aim to detect if a particular data point was used in training a model. We design a novel statistical test to perform robust membership inference attacks (RMIA) with low computational overhead. We achieve this by…
In security-sensitive applications, the success of machine learning depends on a thorough vetting of their resistance to adversarial data. In one pertinent, well-motivated attack scenario, an adversary may attempt to evade a deployed system…
Offline reinforcement learning (RL) can learn control policies from static datasets but, like standard RL methods, it requires reward annotations for every transition. In many cases, labeling large datasets with rewards may be costly,…
Finite mixtures of classifiers (a.k.a. randomized ensembles) have been proposed as a way to improve robustness against adversarial attacks. However, existing attacks have been shown to not suit this kind of classifier. In this paper, we…
Evaluating automatically-generated text summaries is a challenging task. While there have been many interesting approaches, they still fall short of human evaluations. We present RISE, a new approach for evaluating summaries by leveraging…
This is an introductory machine-learning course specifically developed with STEM students in mind. Our goal is to provide the interested reader with the basics to employ machine learning in their own projects and to familiarize themself…
Evaluation efforts such as TREC, CLEF, NTCIR and FIRE, alongside public leaderboard such as MS MARCO, are intended to encourage research and track our progress, addressing big questions in our field. However, the goal is not simply to…
Modern students encounter big, messy data sets long before setting foot in our classrooms. Many of our students need to develop skills in exploratory data analysis and multivariate analysis techniques for their jobs after college, but these…
The leaderboard in machine learning competitions is a tool to show the performance of various participants and to compare them. However, the leaderboard quickly becomes no longer accurate, due to hack or overfitting. This article gives two…
In this evolving era of machine learning security, membership inference attacks have emerged as a potent threat to the confidentiality of sensitive data. In this attack, adversaries aim to determine whether a particular point was used…
Unlike the white-box counterparts that are widely studied and readily accessible, adversarial examples in black-box settings are generally more Herculean on account of the difficulty of estimating gradients. Many methods achieve the task by…
Learning to solve tasks from a sparse reward signal is a major challenge for standard reinforcement learning (RL) algorithms. However, in the real world, agents rarely need to solve sparse reward tasks entirely from scratch. More often, we…
As the adoption of machine learning models increases, ensuring robust models against adversarial attacks is increasingly important. With unsupervised machine learning gaining more attention, ensuring it is robust against attacks is vital.…
Reinforcement learning for LLMs is vulnerable to reward hacking, where models exploit shortcuts to maximize reward without solving the intended task. We systematically study this phenomenon in coding tasks using an environment-manipulation…
Influence estimation tools -- such as memorization scores -- are widely used to understand model behavior, attribute training data, and inform dataset curation. However, recent applications in data valuation and responsible machine learning…