Model Stealing for Any Low-Rank Language Model

• URL: http://arxiv.org/abs/2411.07536v1
• Date: Tue, 12 Nov 2024 04:25:31 GMT
• Title: Model Stealing for Any Low-Rank Language Model
• Authors: Allen Liu, Ankur Moitra,
• Abstract summary: We build a theoretical understanding of stealing language models by studying a simple and mathematically tractable setting. Our main result is an efficient algorithm in the conditional query model, for learning any low-rank distribution. This is an interesting example where, at least theoretically, allowing a machine learning model to solve more complex problems at inference time can lead to drastic improvements in its performance.
• Score: 25.16701867917684
• License:
• Abstract: Model stealing, where a learner tries to recover an unknown model via carefully chosen queries, is a critical problem in machine learning, as it threatens the security of proprietary models and the privacy of data they are trained on. In recent years, there has been particular interest in stealing large language models (LLMs). In this paper, we aim to build a theoretical understanding of stealing language models by studying a simple and mathematically tractable setting. We study model stealing for Hidden Markov Models (HMMs), and more generally low-rank language models. We assume that the learner works in the conditional query model, introduced by Kakade, Krishnamurthy, Mahajan and Zhang. Our main result is an efficient algorithm in the conditional query model, for learning any low-rank distribution. In other words, our algorithm succeeds at stealing any language model whose output distribution is low-rank. This improves upon the previous result by Kakade, Krishnamurthy, Mahajan and Zhang, which also requires the unknown distribution to have high "fidelity", a property that holds only in restricted cases. There are two key insights behind our algorithm: First, we represent the conditional distributions at each timestep by constructing barycentric spanners among a collection of vectors of exponentially large dimension. Second, for sampling from our representation, we iteratively solve a sequence of convex optimization problems that involve projection in relative entropy to prevent compounding of errors over the length of the sequence. This is an interesting example where, at least theoretically, allowing a machine learning model to solve more complex problems at inference time can lead to drastic improvements in its performance.

Related papers

• Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines [74.42485647685272]
  We focus on Generative Masked Language Models (GMLMs) We train a model to fit conditional probabilities of the data distribution via masking, which are subsequently used as inputs to a Markov Chain to draw samples from the model. We adapt the T5 model for iteratively-refined parallel decoding, achieving 2-3x speedup in machine translation with minimal sacrifice in quality.
  arXiv  Detail & Related papers  (2024-07-22T18:00:00Z)
• CodeArt: Better Code Models by Attention Regularization When Symbols Are Lacking [12.458135956476639]
  Transformer based code models have impressive performance in many software engineering tasks. However, their effectiveness degrades when symbols are missing or not informative. We propose a new method to pre-train general code models when symbols are lacking.
  arXiv  Detail & Related papers  (2024-02-19T05:13:22Z)
• Oracle Inequalities for Model Selection in Offline Reinforcement Learning [105.74139523696284]
  We study the problem of model selection in offline RL with value function approximation. We propose the first model selection algorithm for offline RL that achieves minimax rate-optimal inequalities up to logarithmic factors. We conclude with several numerical simulations showing it is capable of reliably selecting a good model class.
  arXiv  Detail & Related papers  (2022-11-03T17:32:34Z)
• Quark: Controllable Text Generation with Reinforced Unlearning [68.07749519374089]
  Large-scale language models often learn behaviors that are misaligned with user expectations. We introduce Quantized Reward Konditioning (Quark), an algorithm for optimizing a reward function that quantifies an (un)wanted property. For unlearning toxicity, negative sentiment, and repetition, our experiments show that Quark outperforms both strong baselines and state-of-the-art reinforcement learning methods.
  arXiv  Detail & Related papers  (2022-05-26T21:11:51Z)
• Low-Rank Constraints for Fast Inference in Structured Models [110.38427965904266]
  This work demonstrates a simple approach to reduce the computational and memory complexity of a large class of structured models. Experiments with neural parameterized structured models for language modeling, polyphonic music modeling, unsupervised grammar induction, and video modeling show that our approach matches the accuracy of standard models at large state spaces.
  arXiv  Detail & Related papers  (2022-01-08T00:47:50Z)
• Outlier-Robust Learning of Ising Models Under Dobrushin's Condition [57.89518300699042]
  We study the problem of learning Ising models satisfying Dobrushin's condition in the outlier-robust setting where a constant fraction of the samples are adversarially corrupted. Our main result is to provide the first computationally efficient robust learning algorithm for this problem with near-optimal error guarantees.
  arXiv  Detail & Related papers  (2021-02-03T18:00:57Z)
• Goal-directed Generation of Discrete Structures with Conditional Generative Models [85.51463588099556]
  We introduce a novel approach to directly optimize a reinforcement learning objective, maximizing an expected reward. We test our methodology on two tasks: generating molecules with user-defined properties and identifying short python expressions which evaluate to a given target value.
  arXiv  Detail & Related papers  (2020-10-05T20:03:13Z)
• Characterizing and Avoiding Problematic Global Optima of Variational Autoencoders [28.36260646471421]
  Variational Auto-encoders (VAEs) are deep generative latent variable models. Recent work shows that traditional training methods tend to yield solutions that violate desiderata. We show that both issues stem from the fact that the global optima of the VAE training objective often correspond to undesirable solutions.
  arXiv  Detail & Related papers  (2020-03-17T15:14:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.