Related papers: Normalising Lustre Preserves Security
Fine-tuning large language models (LLMs) to adapt to evolving safety policies is costly and impractical. Mechanistic interpretability enables inference-time control through latent activation steering, yet its potential for precise,…
Current approaches to LLM safety fundamentally rely on a brittle cat-and-mouse game of identifying and blocking known threats via guardrails. We argue for a fresh approach: robust safety comes not from enumerating what is harmful, but from…
Language Modelling has been a central part of Natural Language Processing for a very long time and in the past few years LSTM-based language models have been the go-to method for commercial language modeling. Recently, it has been shown…
Joint intent detection and slot filling, which is also termed as joint NLU (Natural Language Understanding) is invaluable for smart voice assistants. Recent advancements in this area have been heavily focusing on improving accuracy using…
We introduce a provably stable variant of neural ordinary differential equations (neural ODEs) whose trajectories evolve on an energy functional parametrised by a neural network. Stable neural flows provide an implicit guarantee on…
Modern programmable network switches can implement custom applications using efficient packet processing hardware, and the programming language P4 provides high-level constructs to program such switches. The increase in speed and…
This paper proposes a guaranteed defense method for large language models (LLMs) to safeguard against jailbreaking attacks. Drawing inspiration from the denoised-smoothing approach in the adversarial defense domain, we propose a novel…
Spoken Language Understanding (SLU) is the problem of extracting the meaning from speech utterances. It is typically addressed as a two-step problem, where an Automatic Speech Recognition (ASR) model is employed to convert speech into text,…
With data privacy becoming more of a necessity than a luxury in today's digital world, research on more robust models of privacy preservation and information security is on the rise. In this paper, we take a look at Natural Language…
Structured outputs are essential for large language models (LLMs) in critical applications like agents and information extraction. Despite their capabilities, LLMs often generate outputs that deviate from predefined schemas, significantly…
We define an extension of lambda-calculus with dependents types that enables us to encode transparent and opaque probabilistic programs and prove a strong normalisation result for it by a reducibility technique. While transparent…
In recent years, there has been a proliferation of declarative logic-based trust management languages and systems proposed to ease the description, configuration, and enforcement of security policies. These systems have different tradeoffs…
Linear and substructural types are powerful tools, but adding them to standard functional programming languages often means introducing extra annotations and typing machinery. We propose a lightweight substructural type system design that…
Diffusion language models (DLMs) are an attractive alternative to autoregressive models because they promise sublinear-time, parallel generation, yet practical gains remain elusive as high-quality samples still demand hundreds of refinement…
Deep learning (DL) models for natural language processing (NLP) tasks often handle private data, demanding protection against breaches and disclosures. Data protection laws, such as the European Union's General Data Protection Regulation…
A Network Intrusion Detection System (NIDS) is an important tool that identifies potential threats to a network. Recently, different flow-based NIDS designs utilizing Machine Learning (ML) algorithms have been proposed as potential…
Common-sense and background knowledge is required to understand natural language, but in most neural natural language understanding (NLU) systems, this knowledge must be acquired from training corpora during learning, and then it is static…
Semantic data fuels many different applications, but is still lacking proper integration into programming languages. Untyped access is error-prone while mapping approaches cannot fully capture the conceptualization of semantic data. In this…
The Spectre speculative side-channel attacks pose formidable threats for security. Research has shown that code following the cryptographic constant-time discipline can be efficiently protected against Spectre v1 using a selective variant…
Intrusion Detection Systems (ids)provide an important layer of security for computer systems and networks, and are becoming more and more necessary as reliance on Internet services increases and systems with sensitive data are more commonly…