Related papers: Position: No Retroactive Cure for Infringement dur…

The issue of group fairness in machine learning models, where certain sub-populations or groups are favored over others, has been recognized for some time. While many mitigation strategies have been proposed in centralized learning, many of…

Machine learning inference should be subject to stringent inference time constraints while ensuring high inference quality, especially in safety-critical (e.g., autonomous driving) and mission-critical (e.g., emotion recognition) contexts.…

We prove a fundamental impossibility theorem: neural networks cannot simultaneously learn well-calibrated confidence estimates with meaningful diversity when trained using binary correct/incorrect supervision. Through rigorous mathematical…

In this paper we discuss the implications of using machine learning for judicial decision-making in situations where human rights may be infringed. We argue that the use of such tools in these situations should be limited due to inherent…

Maintaining predictive accuracy in non-stationary environments requires online model selection to adapt autonomously to unknown distribution shifts. However, existing tuning-free algorithms face a fundamental trade-off between robustness…

Engagement recognition datasets are typically subject-indexed and often contain noisy, subjective supervision, making post-hoc dataset revision a practical problem. Existing noisy-label and data-cleaning methods largely operate at the…

Model fairness is an essential element for Trustworthy AI. While many techniques for model fairness have been proposed, most of them assume that the training and deployment data distributions are identical, which is often not true in…

Reinforcement Learning from Human Feedback (RLHF) or Verifiable Rewards (RLVR) are two key steps in the post-training of modern Language Models (LMs). A common problem is reward hacking, where the policy may exploit inaccuracies of the…

Machine learning models often inherit biases from historical data, raising critical concerns about fairness and accountability. Conventional fairness interventions typically require access to sensitive attributes like gender or race, but…

Imitation learning is a widely used policy learning method that enables intelligent agents to acquire complex skills from expert demonstrations. The input to the imitation learning algorithm is usually composed of both the current…

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…

Studying data memorization in neural language models helps us understand the risks (e.g., to privacy or copyright) associated with models regurgitating training data and aids in the development of countermeasures. Many prior works -- and…

The success of machine learning is fueled by the increasing availability of computing power and large training datasets. The training data is used to learn new models or update existing ones, assuming that it is sufficiently representative…

Machine learning models may inadvertently memorize sensitive, unauthorized, or malicious data, posing risks of privacy breaches, security vulnerabilities, and performance degradation. To address these issues, machine unlearning has emerged…

Recursive retraining of generative models poses a critical representation challenge: when synthetic outputs are curated based on a fixed reward signal, the model tends to collapse onto a narrow set of outputs that over-optimize that…

From a simple text prompt, generative-AI image models can create stunningly realistic and creative images bounded, it seems, by only our imagination. These models have achieved this remarkable feat thanks, in part, to the ingestion of…

Recent studies show that image and video generation models can be prompted to reproduce copyrighted content from their training data, raising serious legal concerns about copyright infringement. Copyrighted characters (e.g., Mario, Batman)…

Model stealing attacks have become a serious concern for deep learning models, where an attacker can steal a trained model by querying its black-box API. This can lead to intellectual property theft and other security and privacy risks. The…

Machine learning models have been shown to leak information violating the privacy of their training set. We focus on membership inference attacks on machine learning models which aim to determine whether a data point was used to train the…

Machine learning involves expensive data collection and training procedures. Model owners may be concerned that valuable intellectual property can be leaked if adversaries mount model extraction attacks. As it is difficult to defend against…