Related papers: Information Flow Control in Machine Learning throu…
Protection of confidential data is an important security consideration of today's applications. Of particular concern is to guard against unintentional leakage to a (malicious) observer, who may interact with the program and draw inference…
Many important security problems in JavaScript, such as browser extension security, untrusted JavaScript libraries and safe integration of mutually distrustful websites (mash-ups), may be effectively addressed using an efficient…
Noninterference guarantees that an attacker cannot infer secrets by interacting with a program. Information flow control (IFC) type systems assert noninterference by tracking the level of information learned (pc) and disallowing…
Modern machine learning systems use models trained on ever-growing corpora. Typically, metadata such as ownership, access control, or licensing information is ignored during training. Instead, to mitigate privacy risks, we rely on generic…
Static information flow control (IFC) systems provide the ability to restrict data flows within a program, enabling vulnerable functionality or confidential data to be statically isolated from unsecured data or program logic. Despite the…
This tutorial provides a complete and homogeneous account of the latest advances in fine- and coarse-grained dynamic information-flow control (IFC) security. Since the 70s, the programming language and the operating system communities have…
Language-based information flow control (IFC) enables reasoning about and enforcing security policies in decentralized applications. While information flow properties are relatively extensional and compositional, designing expressive…
This work's main goal is to understand if Information Flow Control (IFC), a security technique used for discovering leaks in software, could be used to indicate the presence of dynamic semantic conflicts between developers contributions in…
Rising device use and third-party IP integration in semiconductors raise security concerns. Unauthorized access, fault injection, and privacy invasion are potential threats from untrusted actors. Different security techniques have been…
The cloud model's dependence on massive parallelism and resource sharing exacerbates the security challenge of timing side-channels. Timing Information Flow Control (TIFC) is a novel adaptation of IFC techniques that may offer a way to…
Ensuring safety in the sense of constraint satisfaction for learning-based control is a critical challenge, especially in the model-free case. While safety filters address this challenge in the model-based setting by modifying unsafe…
Learning-based control has attracted significant attention in recent years, especially for plants that are difficult to model based on first-principles. A key issue in learning-based control is how to make efficient use of data as the…
As AI agents become increasingly autonomous and capable, ensuring their security against vulnerabilities such as prompt injection becomes critical. This paper explores the use of information-flow control (IFC) to provide security guarantees…
Recent advances in artificial intelligence (AI) have enabled effective perception and language models for robots, but their deployment remains computationally expensive, increasing latency and energy use. This work presents the Open…
Secure software architecture is increasingly important in a data-driven world. When security is neglected sensitive information might leak through unauthorized access. To mitigate this software architects needs tools and methods to quantify…
Information Flow Control (IFC) is a collection of techniques for ensuring a no-write-down no-read-up style security policy known as noninterference. Traditional methods for both static and dynamic IFC suffer from untenable numbers of false…
MeanFlow (MF) has recently been established as a framework for one-step generative modeling. However, its ``fastforward'' nature introduces key challenges in both the training objective and the guidance mechanism. First, the original MF's…
Influence functions are commonly used to attribute model behavior to training documents. We explore the reverse: crafting training data that induces model behavior. Our framework, Infusion, uses scalable influence-function approximations to…
Continual learning (CL) is a setting in which an agent has to learn from an incoming stream of data sequentially. CL performance evaluates the model's ability to continually learn and solve new problems with incremental available…
Language-based information flow control (IFC) tracks dependencies within a program using sensitivity labels and prohibits public outputs from depending on secret inputs. In particular, literature has proposed several type systems for…