相关论文: InterPol: De-anonymizing LM Arena via Interpolated…

Prediction and interpolation for long-range video data involves the complex task of modeling motion trajectories for each visible object, occlusions and dis-occlusions, as well as appearance changes due to viewpoint and lighting. Optical…

The use of personal data for training machine learning systems comes with a privacy threat and measuring the level of privacy of a model is one of the major challenges in machine learning today. Identifying training data based on a trained…

In practice, preference learning from human feedback depends on incomplete data with hidden context. Hidden context refers to data that affects the feedback received, but which is not represented in the data used to train a preference…

Learning from preference labels plays a crucial role in fine-tuning large language models. There are several distinct approaches for preference fine-tuning, including supervised learning, on-policy reinforcement learning (RL), and…

Membership inference attacks seek to infer the membership of individual training instances of a privately trained model. This paper presents a membership privacy analysis and evaluation system, called MPLens, with three unique…

Many machine learning adversarial attacks find adversarial samples of a victim model ${\mathcal M}$ by following the gradient of some attack objective functions, either explicitly or implicitly. To confuse and detect such attacks, we take…

This paper studies the training-testing discrepancy (a.k.a. exposure bias) problem for improving the diffusion models. During training, the input of a prediction network at one training timestep is the corresponding ground-truth noisy data…

Color theme or color palette can deeply influence the quality and the feeling of a photograph or a graphical design. Although color palettes may come from different sources such as online crowd-sourcing, photographs and graphical designs,…

User-driven privacy allows individuals to control whether and at what granularity their data is shared, leading to datasets that mix original, generalized, and missing values within the same records and attributes. While such…

Large language models (LLMs) are trained on massive corpora that may contain sensitive information, creating privacy risks under membership inference attacks (MIAs). Knowledge distillation is widely used to compress LLMs into smaller…

LLMs are increasingly used to make or support high-stakes decisions under uncertainty, where alignment depends not only on factual accuracy but on how models weigh tradeoffs between different outcomes. We present an empirical pipeline for…

Large pretrained language models (LLMs) have shown surprising In-Context Learning (ICL) ability. An important application in deploying large language models is to augment LLMs with a private database for some specific task. The main problem…

Differential Privacy (DP) provides an elegant mathematical framework for defining a provable disclosure risk in the presence of arbitrary adversaries; it guarantees that whether an individual is in a database or not, the results of a DP…

We develop an interpolation-based modeling framework for parameter-dependent partial differential equations arising in control, inverse problems, and uncertainty quantification. The solution is discretized in the physical domain using…

Machine learning models, especially deep neural networks have been shown to be susceptible to privacy attacks such as membership inference where an adversary can detect whether a data point was used for training a black-box model. Such…

Recent studies have shown that large language models (LLMs) can infer private user attributes (e.g., age, location, gender) from user-generated text shared online, enabling rapid and large-scale privacy breaches. Existing…

Preference optimization is widely used to align large language models (LLMs) with human preferences. However, many margin-based methods also suppress the chosen response when they try to suppress the rejected one, and there is no general…

Adversarial robustness, the ability of a model to withstand manipulated inputs that cause errors, is essential for ensuring the trustworthiness of machine learning models in real-world applications. However, previous studies have shown that…

Machine learning (ML) systems are increasingly deployed in high-stakes domains where reliability is paramount. This thesis investigates how uncertainty estimation can enhance the safety and trustworthiness of ML, focusing on selective…

Rapid advances in Natural Language Processing (NLP) have revolutionized many fields, including healthcare. However, these advances raise significant privacy concerns, especially when pre-trained models fine-tuned and specialized on…