Related papers: Pop Quiz Attack: Black-box Membership Inference At…
Fine-tuning has emerged as a critical process in leveraging Large Language Models (LLMs) for specific downstream tasks, enabling these models to achieve state-of-the-art performance across various domains. However, the fine-tuning process…
In recent years, Large Language Models (LLMs) have gained widespread use, raising concerns about their security. Traditional jailbreak attacks, which often rely on the model internal information or have limitations when exploring the unsafe…
Transfer learning is a useful machine learning framework that allows one to build task-specific models (student models) without significantly incurring training costs using a single powerful model (teacher model) pre-trained with a large…
With the development of information science and technology, various industries have generated massive amounts of data, and machine learning is widely used in the analysis of big data. However, if the privacy of machine learning…
With large language models (LLMs) poised to become embedded in our daily lives, questions are starting to be raised about the data they learned from. These questions range from potential bias or misinformation LLMs could retain from their…
The rapid advancements of Large Language Models (LLMs) tightly associate with the expansion of the training data size. However, the unchecked ultra-large-scale training sets introduce a series of potential risks like data contamination,…
Membership Inference Attacks (MIAs) on pre-trained Large Language Models (LLMs) aim at determining if a data point was part of the model's training set. Prior MIAs that are built for classification models fail at LLMs, due to ignoring the…
Vision-Language Models (VLMs), built on pre-trained vision encoders and large language models (LLMs), have shown exceptional multi-modal understanding and dialog capabilities, positioning them as catalysts for the next technological…
Indirect Prompt Injection attacks exploit the inherent limitation of Large Language Models (LLMs) to distinguish between instructions and data in their inputs. Despite numerous defense proposals, the systematic evaluation against adaptive…
Knowledge erasure in large language models (LLMs) is important for ensuring compliance with data and AI regulations, safeguarding user privacy, mitigating bias, and misinformation. Existing unlearning methods aim to make the process of…
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…
Privacy attacks on Machine Learning (ML) models often focus on inferring the existence of particular data points in the training data. However, what the adversary really wants to know is if a particular individual's (subject's) data was…
Despite their impressive performance on diverse tasks, large language models (LMs) still struggle with tasks requiring rich world knowledge, implying the limitations of relying solely on their parameters to encode a wealth of world…
Neural language models are black-boxes--both linguistic patterns and factual knowledge are distributed across billions of opaque parameters. This entangled encoding makes it difficult to reliably inspect, verify, or update specific facts.…
Recent advances in large language models (LLMs) significantly boost their usage in software engineering. However, training a well-performing LLM demands a substantial workforce for data collection and annotation. Moreover, training datasets…
Ensuring the security of large language models (LLMs) is an ongoing challenge despite their widespread popularity. Developers work to enhance LLMs security, but vulnerabilities persist, even in advanced versions like GPT-4. Attackers…
It is critical to understand the privacy and robustness vulnerabilities of machine learning models, as their implementation expands in scope. In membership inference attacks, adversaries can determine whether a particular set of data was…
With the rapid advancement of diffusion-based image-generative models, the quality of generated images has become increasingly photorealistic. Moreover, with the release of high-quality pre-trained image-generative models, a growing number…
Neural ranking models (NRMs) have been shown to be highly effective in terms of retrieval performance. Unfortunately, they have also displayed a higher degree of sensitivity to attacks than previous generation models. To help expose and…
The parameter counts of the most widely used large language models (LLMs) are often withheld by their developers, leaving model size -- a primary reference point for interpreting capabilities and costs -- largely undisclosed. We propose a…