Related papers: Differentially Private Language Models Benefit fro…
Generating tabular data under differential privacy (DP) protection ensures theoretical privacy guarantees but poses challenges for training machine learning models, primarily due to the need to capture complex structures under noisy…
Differential privacy (DP) is a gold-standard concept of measuring and guaranteeing privacy in data analysis. It is well-known that the cost of adding DP to deep learning model is its accuracy. However, it remains unclear how it affects…
Large language models specialized for code (CodeLLMs) have demonstrated remarkable capabilities in generating code snippets, documentation, and test cases. However, despite their promising capabilities, CodeLLMs can inadvertently memorize…
The remarkable ability of language models (LMs) has also brought challenges at the interface of AI and security. A critical challenge pertains to how much information these models retain and leak about the training data. This is…
ML models are ubiquitous in real world applications and are a constant focus of research. At the same time, the community has started to realize the importance of protecting the privacy of ML training data. Differential Privacy (DP) has…
Deep learning models have been extensively adopted in various regions due to their ability to represent hierarchical features, which highly rely on the training set and procedures. Thus, protecting the training process and deep learning…
Fine-tuning large language models on downstream tasks is crucial for realizing their cross-domain potential but often relies on sensitive data, raising privacy concerns. Differential privacy (DP) offers rigorous privacy guarantees and has…
While modern machine learning models rely on increasingly large training datasets, data is often limited in privacy-sensitive domains. Generative models trained with differential privacy (DP) on sensitive data can sidestep this challenge,…
Large language models are shown to memorize privacy information such as social security numbers in training data. Given the sheer scale of the training corpus, it is challenging to screen and filter these privacy data, either manually or…
Local differential privacy (LDP) has become a central topic in data privacy research, offering strong privacy guarantees by perturbing user data at the source and removing the need for a trusted curator. However, the noise introduced by LDP…
Differential privacy (DP) is a prominent method for protecting information about individuals during data analysis. Training neural networks with differentially private stochastic gradient descent (DPSGD) influences the model's learning…
Differentially private learning on real-world data poses challenges for standard machine learning practice: privacy guarantees are difficult to interpret, hyperparameter tuning on private data reduces the privacy budget, and ad-hoc privacy…
Privacy concerns have attracted increasing attention in data-driven products due to the tendency of machine learning models to memorize sensitive training data. Generating synthetic versions of such data with a formal privacy guarantee,…
Large multimodal language models have proven transformative in numerous applications. However, these models have been shown to memorize and leak pre-training data, raising serious user privacy and information security concerns. While data…
We study private prediction where differential privacy is achieved by adding noise to the outputs of a non-private model. Existing methods rely on noise proportional to the global sensitivity of the model, often resulting in sub-optimal…
Practitioners commonly download pretrained machine learning models from open repositories and finetune them to fit specific applications. We show that this practice introduces a new risk of privacy backdoors. By tampering with a pretrained…
The pre-training and fine-tuning paradigm has demonstrated its effectiveness and has become the standard approach for tailoring language models to various tasks. Currently, community-based platforms offer easy access to various pre-trained…
Differentially private (DP) machine learning allows us to train models on private data while limiting data leakage. DP formalizes this data leakage through a cryptographic game, where an adversary must predict if a model was trained on a…
Language model alignment is crucial for ensuring that large language models (LLMs) align with human preferences, yet it often involves sensitive user data, raising significant privacy concerns. While prior work has integrated differential…
Protecting large language models from privacy leakage is becoming increasingly crucial with their wide adoption in real-world products. Yet applying differential privacy (DP), a canonical notion with provable privacy guarantees for machine…