Related papers: No More, No Less: Least-Privilege Language Models
Most Transformer language models are primarily pretrained on English text, limiting their use for other languages. As the model sizes grow, the performance gap between English and other languages with fewer compute and data resources…
Delimited control is a powerful mechanism for programming language extension which has been recently proposed for Prolog (and implemented in SWI-Prolog). By manipulating the control flow of a program from inside the language, it enables the…
Local differential privacy (LDP) is a model where users send privatized data to an untrusted central server whose goal it to solve some data analysis task. In the non-interactive version of this model the protocol consists of a single round…
With the widespread adoption of edge computing technologies and the increasing prevalence of deep learning models in these environments, the security risks and privacy threats to models and data have grown more acute. Attackers can exploit…
Robust access control is a cornerstone of secure software, systems, and networks. An access control mechanism is as effective as the policy it enforces. However, authoring effective policies that satisfy desired properties such as the…
Delimited control is a powerful mechanism for programming language extension which has been recently proposed for Prolog (and implemented in SWI-Prolog). By manipulating the control flow of a program from inside the language, it enables the…
A multiplicity queue is a concurrently-defined data type which relaxes the conditions of a linearizable FIFO queue to allow concurrent Dequeue instances to return the same value. It would seem that this should allow faster implementations,…
Noninterference is a popular semantic security condition because it offers strong end-to-end guarantees, it is inherently compositional, and it can be enforced using a simple security type system. Unfortunately, it is too restrictive for…
For computer software, our security models, policies, mechanisms, and means of assurance were primarily conceived and developed before the end of the 1970's. However, since that time, software has changed radically: it is thousands of times…
Backdoor attacks are among the most effective, practical, and stealthy attacks in deep learning. In this paper, we consider a practical scenario where a developer obtains a deep model from a third party and uses it as part of a…
Information-flow security type systems ensure confidentiality by enforcing noninterference: a program cannot leak private data to public channels. However, in practice, programs need to selectively declassify information about private data.…
It is crucial for large language models (LLMs) to follow instructions that involve multiple constraints. However, it is an unexplored area to enhance LLMs' ability to follow soft constraints. To bridge the gap, we initially design a…
Clustering software into peer groups based on its apparent functionality allows for simple, intuitive categorization of software that can, in particular, help identify which software uses comparatively more privilege than is necessary to…
Machine learning models deployed as a service (MLaaS) are susceptible to model stealing attacks, where an adversary attempts to steal the model within a restricted access framework. While existing attacks demonstrate near-perfect…
Cloud computing has changed the way enterprises store, access and share data. Data is constantly being uploaded to the cloud and shared within an organization built on a hierarchy of many different individuals that are given certain data…
Access control is fundamental to computer security, and has thus been the subject of extensive formal study. In particular, *relative expressiveness analysis* techniques have used formal mappings called *simulations* to explore whether one…
Frontier models are currently developed and distributed primarily through two channels: centralized proprietary APIs or open-sourcing of pre-trained weights. We identify a third paradigm - Protocol Learning - where models are trained across…
Deep reinforcement learning policies, which are integral to modern control systems, represent valuable intellectual property. The development of these policies demands considerable resources, such as domain expertise, simulation fidelity,…
The problems which are important for the effective functioning of an access control policy in a large information system (LIS) are selected. The general concept of a local optimization of a role-based access control (RBAC) model is…
Despite the success of style transfer in image processing, it has seen limited progress in natural language generation. Part of the problem is that content is not as easily decoupled from style in the text domain. Curiously, in the field of…