相关论文: On the Evidentiary Limits of Membership Inference …

Machine unlearning (MU) is essential for enforcing the right to be forgotten in machine learning systems. A key challenge of MU is how to reliably audit whether a model has truly forgotten specified training data. Membership Inference…

Determining whether a dataset was part of a machine learning model's training data pool can reveal privacy vulnerabilities, a challenge often addressed through membership inference attacks (MIAs). Traditional MIAs typically require access…

Large vision-language models (LVLMs) derive their capabilities from extensive training on vast corpora of visual and textual data. Empowered by large-scale parameters, these models often exhibit strong memorization of their training data,…

With the surge of large language models (LLMs), Large Vision-Language Models (VLMs)--which integrate vision encoders with LLMs for accurate visual grounding--have shown great potential in tasks like generalist agents and robotic control.…

A Membership Inference Attack (MIA) assesses how much a target machine learning model reveals about its training data by determining whether specific query instances were part of the training set. State-of-the-art MIAs rely on training…

The remarkable language ability of Large Language Models (LLMs) stems from extensive training on vast datasets, often including copyrighted material, which raises serious concerns about unauthorized use. While Membership Inference Attacks…

Large language models sometimes inadvertently reproduce passages that are copyrighted, exposing downstream applications to legal risk. Most existing studies for inference-time defences focus on surface-level token matching and rely on…

Among all privacy attacks against Machine Learning (ML), membership inference attacks (MIA) attracted the most attention. In these attacks, the attacker is given an ML model and a data point, and they must infer whether the data point was…

Language models (LMs) derive their capabilities from extensive training on diverse data, including potentially copyrighted material. These models can memorize and generate content similar to their training data, posing potential concerns.…

Membership inference attacks (MIAs) aim to determine whether specific data were used to train a model. While extensively studied on classification models, their impact on time series forecasting remains largely unexplored. We address this…

Large Language Models (LLMs) remain vulnerable to optimization-based jailbreak attacks that exploit internal gradient structure. While Sparse Autoencoders (SAEs) are widely used for interpretability, their robustness implications remain…

Membership inference attacks (MIAs) on diffusion models have emerged as potential evidence of unauthorized data usage in training pre-trained diffusion models. These attacks aim to detect the presence of specific images in training datasets…

Neural models for vulnerability prediction (VP) have achieved impressive performance by learning from large-scale code repositories. However, their susceptibility to Membership Inference Attacks (MIAs), where adversaries aim to infer…

Large Language Models (LLMs) have revolutionized Natural Language Processing (NLP) but pose risks of inadvertently exposing copyrighted or proprietary data, especially when such data is used for training but not intended for distribution.…

In this paper we develop state-of-the-art privacy attacks against Large Language Models (LLMs), where an adversary with some access to the model tries to learn something about the underlying training data. Our headline results are new…

Training machine learning models on privacy-sensitive data has become a popular practice, driving innovation in ever-expanding fields. This has opened the door to new attacks that can have serious privacy implications. One such attack, the…

Recent work in the privacy literature shows that sample-targeted membership inference attacks (MIAs) significantly outperform untargeted approaches by a wide margin. Motivated by this observation, we address the following question: can the…

With the emergence of powerful large-scale foundation models, the training paradigm is increasingly shifting from from-scratch training to transfer learning. This enables high utility training with small, domain-specific datasets typical in…

Membership Inference Attack (MIA) aims to determine whether a specific data sample was included in the training dataset of a target model. Traditional MIA approaches rely on shadow models to mimic target model behavior, but their…

Recommender systems (RecSys) have been widely applied to various applications, including E-commerce, finance, healthcare, social media and have become increasingly influential in shaping user behavior and decision-making, highlighting their…