Related papers: LAMP: Extracting Text from Gradients with Language…
Federated learning synchronizes models through gradient transmission and aggregation. However, these gradients pose significant privacy risks, as sensitive training data is embedded within them. Existing gradient inversion attacks suffer…
Retrieval augmented generation (RAG) is frequently used to mitigate hallucinations and provide up-to-date knowledge for large language models (LLMs). However, given that document retrieval is an imprecise task and sometimes results in…
Large Language Models~(LLMs) struggle with providing current information due to the outdated pre-training data. Existing methods for updating LLMs, such as knowledge editing and continual fine-tuning, have significant drawbacks in…
Retrieval Augmented Generation (RAG) frameworks improve the accuracy of large language models (LLMs) by integrating external knowledge from retrieved documents, thereby overcoming the limitations of models' static intrinsic knowledge.…
Traditional RLHF optimizes language models with coarse, scalar rewards that mask the fine-grained reasons behind success or failure, leading to slow and opaque learning. Recent work augments RL with textual critiques through prompting or…
Recent large-scale natural language processing (NLP) systems use a pre-trained Large Language Model (LLM) on massive and diverse corpora as a headstart. In practice, the pre-trained model is adapted to a wide array of tasks via fine-tuning…
Gradient inversion attack (or input recovery from gradient) is an emerging threat to the security and privacy preservation of Federated learning, whereby malicious eavesdroppers or participants in the protocol can recover (partially) the…
Retrieval-augmented generation (RAG) improves the response quality of large language models (LLMs) by retrieving knowledge from external databases. Typical RAG approaches split the text database into chunks, organizing them in a flat…
With the large-scale adoption of Large Language Models (LLMs) in various applications, there is a growing reliability concern due to their tendency to generate inaccurate text, i.e. hallucinations. In this work, we propose Cross-Layer…
It is widely believed that sharing gradients will not leak private training data in distributed learning systems such as Collaborative Learning and Federated Learning, etc. Recently, Zhu et al. presented an approach which shows the…
Natural language processing (NLP) models have become increasingly popular in real-world applications, such as text classification. However, they are vulnerable to privacy attacks, including data reconstruction attacks that aim to extract…
Hallucination mitigation remains a persistent challenge for large language models (LLMs), even as model scales grow. Existing approaches often rely on external knowledge sources, such as structured databases or knowledge graphs, accessed…
Federated learning (FL) has become a key component in various language modeling applications such as machine translation, next-word prediction, and medical record analysis. These applications are trained on datasets from many FL…
We present REMARK-LLM, a novel efficient, and robust watermarking framework designed for texts generated by large language models (LLMs). Synthesizing human-like content using LLMs necessitates vast computational resources and extensive…
A central tenet of Federated learning (FL), which trains models without centralizing user data, is privacy. However, previous work has shown that the gradient updates used in FL can leak user information. While the most industrial uses of…
As Large Language Models (LLMs) continue to evolve, more are being designed to handle long-context inputs. Despite this advancement, most of them still face challenges in accurately handling long-context tasks, often showing the "lost in…
Large language models (LLMs) are increasingly deployed in high-stakes domains, yet a unified treatment of their overlapping safety challenges remains lacking. We present SafeLM, a framework that jointly addresses four pillars of LLM safety:…
Exchanging gradients is a widely used method in modern multi-node machine learning system (e.g., distributed training, collaborative learning). For a long time, people believed that gradients are safe to share: i.e., the training data will…
Federated learning enables collaborative machine learning while preserving data privacy. However, the rise of federated unlearning, designed to allow clients to erase their data from the global model, introduces new privacy concerns.…
Using mathematical modeling and human subjects experiments, this research explores the extent to which emerging webcams might leak recognizable textual and graphical information gleaming from eyeglass reflections captured by webcams. The…