Related papers: Types for Information Flow Control: Labeling Granu…

As large language models continue to develop and expand, the extensive public data they rely on faces the risk of depletion. Consequently, leveraging private data within organizations to enhance the performance of large models has emerged…

Fine-grained emotion recognition aims to identify the emotional type in queries through reasoning and decision-making processes, playing a crucial role in various systems. Recent methods use In-Context Learning (ICL), enhancing the…

In-context learning (ICL) i.e. showing LLMs only a few task-specific demonstrations has led to downstream gains with no task-specific fine-tuning required. However, LLMs are sensitive to the choice of prompts, and therefore a crucial…

The Information Flow Framework (IFF) is a descriptive category metatheory. It is an experiment in foundations, which follows a bottom-up approach to logical description. The IFF forms the structural aspect of the IEEE P1600.1 Standard Upper…

While Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in general visual understanding, they frequently falter in fine-grained perception tasks that require identifying tiny objects or discerning subtle…

The capability of in-context learning (ICL) enables large language models (LLMs) to perform novel tasks without parameter updates by conditioning on a few input-output examples. However, collecting high-quality examples for new or…

In this thesis we consider the problem of information hiding in the scenarios of interactive systems, statistical disclosure control, and refinement of specifications. We apply quantitative approaches to information flow in the first two…

Information flow properties express the capability for an agent to infer information about secret behaviours of a partially observable system. In a language-theoretic setting, where the system behaviour is described by a language, we define…

In-context learning (ICL) is the ability of a large language model (LLM) to learn a new task from a few demonstrations presented as part of the context. Past studies have attributed a large portion of the success of ICL to the way these…

Instruction following is a critical ability for Large Language Models to perform downstream tasks. The standard approach to instruction tuning has relied on a specific phase of supervised fine-tuning over curated instruction datasets,…

Type systems designed for information-flow control commonly use a program-counter label to track the sensitivity of the context and rule out data leakage arising from effectful computation in a sensitive context. Currently, type-system…

Information flow analysis checks whether certain pieces of (confidential) data may affect the results of computations in unwanted ways and thus leak information. Dynamic information flow analysis adds instrumentation code to the target…

Fine grained information flow monitoring can in principle address a wide range of security and privacy goals, for example in web applications. But it is very difficult to achieve sound monitoring with acceptable runtime cost and sufficient…

Effective organization of in-context learning (ICL) demonstrations is key to improving the quality of large language model (LLM) responses. To create better sample-label pairs that instruct LLM understanding, we introduce logit…

Language models (LMs) have achieved notable success in numerous NLP tasks, employing both fine-tuning and in-context learning (ICL) methods. While language models demonstrate exceptional performance, they face robustness challenges due to…

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…

Existing entity typing systems usually exploit the type hierarchy provided by knowledge base (KB) schema to model label correlations and thus improve the overall performance. Such techniques, however, are not directly applicable to more…

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…

Affine type systems are substructural type systems where copying of information is restricted, but discarding of information is permissible at all types. Such type systems are well-suited for describing quantum programming languages,…

The rise of serverless computing provides an opportunity to rethink cloud security. We present an approach for securing serverless systems using a novel form of dynamic information flow control (IFC). We show that in serverless…