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

Learned index structures aim to accelerate queries by training machine learning models to approximate the rank function associated with a database attribute. While effective in practice, their theoretical limitations are not fully…

The performance of multilingual pretrained models is highly dependent on the availability of monolingual or parallel text present in a target language. Thus, the majority of the world's languages cannot benefit from recent progress in NLP…

Recent AI regulations call for data that remain useful for innovation while resistant to misuse, balancing utility with protection at the model level. Existing approaches either perturb data to make it unlearnable or retrain models to…

The dominance of large decoder-only language models has overshadowed encoder-decoder architectures, despite their fundamental efficiency advantages in sequence processing. For small language models (SLMs) - those with 1 billion parameters…

This paper introduces language-based agent control (LBAC), a new programming model for agentic applications that brings techniques from programming languages and language-based security to the problem of agent control. In conventional…

Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings. Despite the…

Current research in adversarial robustness of LLMs focuses on discrete input manipulations in the natural language space, which can be directly transferred to closed-source models. However, this approach neglects the steady progression of…

Access control needs have broad design implications, but access control specifications may be elicited before, during, or after these needs are captured. Because access control knowledge is distributed, we need to make knowledge asymmetries…

Model extraction attacks pose significant security threats to deployed language models, potentially compromising intellectual property and user privacy. This survey provides a comprehensive taxonomy of LLM-specific extraction attacks and…

We study a new vulnerability in commercial-scale safety-aligned large language models (LLMs): their refusal to generate harmful responses can be broken by flipping only a few bits in model parameters. Our attack jailbreaks billion-parameter…

Distributed data analytics platforms (i.e., Apache Spark, Hadoop) provide high-level APIs to programmatically write analytics tasks that are run distributedly in multiple computing nodes. The design of these frameworks was primarily…

Large language models (LLMs) are primarily accessed via commercial APIs, but this often requires users to expose their data to service providers. In this paper, we explore how users can stay in control of their data by using privacy…

The rapid development of language models (LMs) brings unprecedented accessibility and usage for both models and users. On the one hand, powerful LMs achieve state-of-the-art performance over numerous downstream NLP tasks. On the other hand,…

Shared control combines human intention with autonomous decision-making. At the low level, the primary goal is to maintain safety regardless of the user's input to the system. However, existing shared control methods-based on, e.g., Model…

System prompts are critical for guiding the behavior of Large Language Models (LLMs), yet they often contain proprietary logic or sensitive information, making them a prime target for extraction attacks. Adversarial queries can successfully…

Machine learning systems deployed in distributed or federated environments are highly susceptible to adversarial manipulations, particularly availability attacks -adding imperceptible perturbations to training data, thereby rendering the…

Pre-trained Natural Language Processing (NLP) models can be easily adapted to a variety of downstream language tasks. This significantly accelerates the development of language models. However, NLP models have been shown to be vulnerable to…

We classify and re-examine some of the current approaches to improve the performance-computes trade-off of language models, including (1) non-causal models (such as masked language models), (2) extension of batch length with efficient…

The rapid rise of Language Models (LMs) has expanded the capabilities of natural language processing, powering applications from text generation to complex decision-making. While state-of-the-art LMs often boast hundreds of billions of…

The privacy of machine learning models has become a significant concern in many emerging Machine-Learning-as-a-Service applications, where prediction services based on well-trained models are offered to users via pay-per-query. The lack of…