On the Impossible Safety of Large AI Models

Large AI Models (LAIMs), of which large language models are the most prominent recent example, showcase some impressive performance. However they have been empirically found to pose serious security issues. This paper systematizes our knowledge about the fundamental impossibility of building arbitrarily accurate and secure machine learning models. More precisely, we identify key challenging features of many of today's machine learning settings. Namely, high accuracy seems to require memorizing large training datasets, which are often user-generated and highly heterogeneous, with both sensitive information and fake users. We then survey statistical lower bounds that, we argue, constitute a compelling case against the possibility of designing high-accuracy LAIMs with strong security guarantees.

Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery

The strength of modern generative models lies in their ability to be controlled through text-based prompts. Typical "hard" prompts are made from interpretable words and tokens, and must be hand-crafted by humans. There are also "soft" prompts, which consist of continuous feature vectors. These can be discovered using powerful optimization methods, but they cannot be easily interpreted, re-used across models, or plugged into a text-based interface. We describe an approach to robustly optimize hard text prompts through efficient gradient-based optimization. Our approach automatically generates hard text-based prompts for both text-to-image and text-to-text applications. In the text-to-image setting, the method creates hard prompts for diffusion models, allowing API users to easily generate, discover, and mix and match image concepts without prior knowledge on how to prompt the model. In the text-to-text setting, we show that hard prompts can be automatically discovered that are effective in tuning LMs for classification.

Stilgherrian on Twitter

“Well this is going pretty much as expected.”

Theory of Mind May Have Spontaneously Emerged in Large Language Models | Hacker News

Kevin Liu on Twitter

“The entire prompt of Microsoft Bing Chat?! (Hi, Sydney.)”

Trading Information between Latents in Hierarchical Variational Autoencoders

Variational Autoencoders (VAEs) were originally motivated (Kingma & Welling, 2014) as probabilistic generative models in which one performs approximate Bayesian inference. The proposal of $β$-VAEs (Higgins et al., 2017) breaks this interpretation and generalizes VAEs to application domains beyond generative modeling (e.g., representation learning, clustering, or lossy data compression) by introducing an objective function that allows practitioners to trade off between the information content ("bit rate") of the latent representation and the distortion of reconstructed data (Alemi et al., 2018). In this paper, we reconsider this rate/distortion trade-off in the context of hierarchical VAEs, i.e., VAEs with more than one layer of latent variables. We identify a general class of inference models for which one can split the rate into contributions from each layer, which can then be tuned independently. We derive theoretical bounds on the performance of downstream tasks as functions of the individual layers' rates and verify our theoretical findings in large-scale experiments. Our results provide guidance for practitioners on which region in rate-space to target for a given application.