Related papers: No More, No Less: Least-Privilege Language Models

Pre-trained general-purpose language models have been a dominating component in enabling real-world natural language processing (NLP) applications. However, a pre-trained model with backdoor can be a severe threat to the applications. Most…

Deep neural networks (DNNs) have become the essential components for various commercialized machine learning services, such as Machine Learning as a Service (MLaaS). Recent studies show that machine learning services face severe privacy…

Can we construct a neural model that is inductively biased towards learning human languages? Motivated by this question, we aim at constructing an informative prior over neural weights, in order to adapt quickly to held-out languages in the…

A lease is an important primitive for building distributed protocols, and it is ubiquitously employed in distributed systems. However, the scope of the classic lease abstraction is restricted to the trusted computing infrastructure.…

We consider non-clairvoyant scheduling with online precedence constraints, where an algorithm is oblivious to any job dependencies and learns about a job only if all of its predecessors have been completed. Given strong impossibility…

This paper discusses that there is significant benefit in providing stronger security at lower layers of the network stack for hosts connected to a network. It claims to reduce the attack vulnerability of a networked host by providing…

Deep Neural Networks (DNNs) are high-value intellectual property (IP), yet deploying them to edge environments exposes them to \textbf{unrestricted oracle access}, rendering them vulnerable to model extraction and inversion attacks.…

Alignment of large language models (LLMs) with human preferences typically relies on supervised reward models or external judges that demand abundant annotations. However, in fields that rely on professional knowledge, such as medicine and…

Language Models (LMs) are becoming increasingly popular in real-world applications. Outsourcing model training and data hosting to third-party platforms has become a standard method for reducing costs. In such a situation, the attacker can…

We consider the point-to-point message passing model of communication in which there are $k$ processors with individual private inputs, each $n$-bit long. Each processor is located at the node of an underlying undirected graph and has…

Aligning large language models (LLMs) to preference data typically assumes a known link function between observed preferences and latent rewards (e.g., a logistic Bradley-Terry link). Misspecification of this link can bias inferred rewards…

The literature on information flow security with respect to transitive policies has been concentrated largely on the case of policies with two security domains, High and Low, because of a presumption that more general policies can be…

We present a novel multi-agent RL approach, Selective Multi-Agent Prioritized Experience Relay, in which agents share with other agents a limited number of transitions they observe during training. The intuition behind this is that even a…

Neural language models often struggle with low-resource languages due to the limited availability of training data, making tokens from these languages rare in the training set. This paper addresses a specific challenge during training: rare…

Preference alignment in Large Language Models (LLMs) has significantly improved their ability to adhere to human instructions and intentions. However, existing direct alignment algorithms primarily focus on relative preferences and often…

Deployment efficiency is an important criterion for many real-world applications of reinforcement learning (RL). Despite the community's increasing interest, there lacks a formal theoretical formulation for the problem. In this paper, we…

Prompt-based learning is vulnerable to backdoor attacks. Existing backdoor attacks against prompt-based models consider injecting backdoors into the entire embedding layers or word embedding vectors. Such attacks can be easily affected by…

Proliferation of systems that generate enormous amounts of data and operate in real time has led researchers to rethink the current organization of the cloud. Many proposed solutions consist of a number of small data centers in the vicinity…

Application containers, such as Docker containers, have recently gained popularity as a solution for agile and seamless deployment of applications. These light-weight virtualization environments run applications that are packed together…

Model Context Protocol (MCP) standardizes interface mapping for large language models (LLMs) to access external data and tools, which revolutionizes the paradigm of tool selection and facilitates the rapid expansion of the LLM agent tool…