相关论文: Context-Aware Membership Inference Attacks against…

Multimodal large language models (MLLMs) demonstrate remarkable capabilities in handling complex multimodal tasks and are increasingly adopted in video understanding applications. However, their rapid advancement raises serious data privacy…

Graph Neural Networks (GNNs), inspired by Convolutional Neural Networks (CNNs), aggregate the message of nodes' neighbors and structure information to acquire expressive representations of nodes for node classification, graph…

Large Language Models (LLMs) have become integral to automated code analysis, enabling tasks such as vulnerability detection and code comprehension. However, their integration introduces novel attack surfaces. In this paper, we identify and…

While large language models (LLMs) are extensively used, there are raising concerns regarding privacy, security, and copyright due to their opaque training data, which brings the problem of detecting pre-training data on the table. Current…

Large language models (LLMs) show strong performance across many applications, but their ability to memorize and potentially reveal training data raises serious privacy concerns. We introduce the PopQuiz Attack, a black-box membership…

Fine-tuning Large Language Models (LLMs) typically involves updating at least a few billions of parameters. A more parameter-efficient approach is Prompt Tuning (PT), which updates only a few learnable tokens, and differently, In-Context…

We propose Fast-MIA (https://github.com/Nikkei/fast-mia), a Python library for efficiently evaluating membership inference attacks (MIA) against large language models (LLMs). MIA has emerged as a crucial technique for auditing privacy risks…

Modern large language models (LLMs) are used in many business applications in general, and specifically in web search systems and applications that generate overviews of search results - LLM Overview systems. Such systems are using an LLM…

When model developers or users fine-tune an LLM, this can induce behaviors that are unexpected, deliberately harmful, or hard to detect. It would be far easier to audit LLMs if they could simply describe their behaviors in natural language.…

Large language models (LLMs) are excellent few-shot learners. They can perform a wide variety of tasks purely based on natural language prompts provided to them. These prompts contain data of a specific downstream task -- often the private…

In Member Inference (MI) attacks, the adversary try to determine whether an instance is used to train a machine learning (ML) model. MI attacks are a major privacy concern when using private data to train ML models. Most MI attacks in the…

The use of large language models (LLMs) in peer review systems has attracted growing attention, making it essential to examine their potential vulnerabilities. Prior attacks rely on prompt injection, which alters manuscript content and…

Large language models (LLMs) have showcased their capability with few-shot inference known as in-context learning. However, in-domain demonstrations are not always readily available in real scenarios, leading to cross-domain in-context…

Most existing membership inference attacks (MIAs) utilize metrics (e.g., loss) calculated on the model's final state, while recent advanced attacks leverage metrics computed at various stages, including both intermediate and final stages,…

Cognitive diagnosis models (CDMs) are pivotal for creating fine-grained learner profiles in modern intelligent education platforms. However, these models are trained on sensitive student data, raising significant privacy concerns. While…

Memorization in large language models (LLMs) makes them vulnerable to data extraction attacks. While pre-training memorization has been extensively studied, fewer works have explored its impact in fine-tuning, particularly for LoRA…

A membership inference attack allows an adversary to query a trained machine learning model to predict whether or not a particular example was contained in the model's training dataset. These attacks are currently evaluated using…

Cognitive biases are systematic deviations in thinking that lead to irrational judgments and problematic decision-making, extensively studied across various fields. Recently, large language models (LLMs) have shown advanced understanding…

This study investigates the efficacy of Large Language Models (LLMs) in causal discovery. Using newly available open-source LLMs, OLMo and BLOOM, which provide access to their pre-training corpora, we investigate how LLMs address causal…

Diffusion models have achieved remarkable progress in image generation, but their increasing deployment raises serious concerns about privacy. In particular, fine-tuned models are highly vulnerable, as they are often fine-tuned on small and…