Related papers: Opponent-Adjusted Evaluation of NFL Pass Blocking …

Traditional (fickle) adversarial examples involve finding a small perturbation that does not change an input's true label but confuses the classifier into outputting a different prediction. Conversely, obstinate adversarial examples occur…

This paper reports on an effort of reproducing the organizers' baseline as well as the top performing participant submission at the 2021 edition of the TREC Conversational Assistance track. TREC systems are commonly regarded as reference…

Evaluating the overall ability of players in the National Hockey League (NHL) is a difficult task. Existing methods such as the famous "plus/minus" statistic have many shortcomings. Standard linear regression methods work well when player…

Regression-based adjusted plus-minus statistics were developed in basketball and have recently come to hockey. The purpose of these statistics is to provide an estimate of each player's contribution to his team, independent of the strength…

Word-level adversarial attacks have shown success in NLP models, drastically decreasing the performance of transformer-based models in recent years. As a countermeasure, adversarial defense has been explored, but relatively few efforts have…

Despite the considerable success enjoyed by machine learning techniques in practice, numerous studies demonstrated that many approaches are vulnerable to attacks. An important class of such attacks involves adversaries changing features at…

The widespread adoption of transfer learning has revolutionized machine learning by enabling efficient adaptation of pre-trained models to new domains. However, the reliability of these adaptations remains poorly understood, particularly…

Attack detection is usually approached as a classification problem. However, standard classification tools often perform poorly because an adaptive attacker can shape his attacks in response to the algorithm. This has led to the recent…

As jailbreaks, adversarially crafted inputs that bypass safety constraints, continue to be discovered in Large Language Models, practitioners increasingly rely on fine-tuning as a defensive strategy. Yet the theoretical foundations…

We study the problem of learning predictors that are robust to adversarial examples with respect to an unknown perturbation set, relying instead on interaction with an adversarial attacker or access to attack oracles, examining different…

Bandit algorithms have recently emerged as a powerful tool for evaluating machine learning models, including generative image models and large language models, by efficiently identifying top-performing candidates without exhaustive…

Reward learning plays a pivotal role in Reinforcement Learning from Human Feedback (RLHF), ensuring the alignment of language models. The Bradley-Terry (BT) model stands as the prevalent choice for capturing human preferences from datasets…

Multi-turn prompt injection follows a known attack path -- trust-building, pivoting, escalation but text-level defenses miss covert attacks where individual turns appear benign. We show this attack path leaves an activation-level signature…

Efforts to address declining accuracy as a result of data shifts often involve various data-augmentation strategies. Adversarial training is one such method, designed to improve robustness to worst-case distribution shifts caused by…

Analysis of player tracking data for American football is in its infancy, since the National Football League (NFL) released its Next Gen Stats tracking data publicly for the first time in December 2018. While tracking datasets in other…

Many applications, e.g. in content recommendation, sports, or recruitment, leverage the comparisons of alternatives to score those alternatives. The classical Bradley-Terry model and its variants have been widely used to do so. The…

In contrast to the classic formulation of partial monitoring, linear partial monitoring can model infinite outcome spaces, while imposing a linear structure on both the losses and the observations. This setting can be viewed as a…

American football games attract significant worldwide attention every year. Identifying players from videos in each play is also essential for the indexing of player participation. Processing football game video presents great challenges…

The increasing deployment of large language models (LLMs) in safety-critical applications raises fundamental challenges in systematically evaluating robustness against adversarial behaviors. Existing red-teaming practices are largely manual…

Machine learning based network intrusion detection systems are vulnerable to adversarial attacks that degrade classification performance under both gradient-based and distribution shift threat models. Existing defenses typically apply…