Related papers: PANORAMIA: Privacy Auditing of Machine Learning Mo…
Transfer learning has been widely studied and gained increasing popularity to improve the accuracy of machine learning models by transferring some knowledge acquired in different training. However, no prior work has pointed out that…
The use of Machine Learning (ML) for data-driven decision-making often relies on access to sensitive datasets, which introduces privacy challenges. Traditional encryption methods protect data at rest or in transit but fail to secure it…
Membership inference attacks (MIAs) against Diffusion Models (DMs) raise pressing privacy concerns by revealing whether a sample was part of the training set. While existing methods typically rely on measuring reconstruction error across…
Large-scale pre-trained models are increasingly adapted to downstream tasks through a new paradigm called prompt learning. In contrast to fine-tuning, prompt learning does not update the pre-trained model's parameters. Instead, it only…
Recently, diffusion models have become popular tools for image synthesis because of their high-quality outputs. However, like other large-scale models, they may leak private information about their training data. Here, we demonstrate a…
Large Reasoning Models (LRMs) have rapidly gained prominence for their strong performance in solving complex tasks. Many modern black-box LRMs expose the intermediate reasoning traces through APIs to improve transparency (e.g., Gemini-2.5…
Fine-tuned language models pose significant privacy risks, as they may memorize and expose sensitive information from their training data. Membership inference attacks (MIAs) provide a principled framework for auditing these risks, yet…
The state-of-the-art for membership inference attacks on machine learning models is a class of attacks based on shadow models that mimic the behavior of the target model on subsets of held-out nonmember data. However, we find that this…
We present two information leakage attacks that outperform previous work on membership inference against generative models. The first attack allows membership inference without assumptions on the type of the generative model. Contrary to…
Learned recommender systems may inadvertently leak information about their training data, leading to privacy violations. We investigate privacy threats faced by recommender systems through the lens of membership inference. In such attacks,…
In distributed learning settings, models are iteratively updated with shared gradients computed from potentially sensitive user data. While previous work has studied various privacy risks of sharing gradients, our paper aims to provide a…
The arms race between attacks and defenses for machine learning models has come to a forefront in recent years, in both the security community and the privacy community. However, one big limitation of previous research is that the security…
Language Models (LMs) typically adhere to a "pre-training and fine-tuning" paradigm, where a universal pre-trained model can be fine-tuned to cater to various specialized domains. Low-Rank Adaptation (LoRA) has gained the most widespread…
OpenLVLM-MIA is a new benchmark that highlights fundamental challenges in evaluating membership inference attacks (MIA) against large vision-language models (LVLMs). While prior work has reported high attack success rates, our analysis…
In machine learning, curation is used to select the most valuable data for improving both model accuracy and computational efficiency. Recently, curation has also been explored as a solution for private machine learning: rather than…
Machine Unlearning (MU) aims to remove target training data from a trained model so that the removed data no longer influences the model's behavior, fulfilling "right to be forgotten" obligations under data privacy laws. Yet, we observe…
A membership inference attack (MIA) poses privacy risks for the training data of a machine learning model. With an MIA, an attacker guesses if the target data are a member of the training dataset. The state-of-the-art defense against MIAs,…
Given the rising popularity of AI-generated art and the associated copyright concerns, identifying whether an artwork was used to train a diffusion model is an important research topic. The work approaches this problem from the membership…
Most current approaches for protecting privacy in machine learning (ML) assume that models exist in a vacuum. Yet, in reality, these models are part of larger systems that include components for training data filtering, output monitoring,…
Recent studies have shown that deep learning models are vulnerable to membership inference attacks (MIAs), which aim to infer whether a data record was used to train a target model or not. To analyze and study these vulnerabilities, various…