相关论文: NeMo Guardrails: A Toolkit for Controllable and Sa…

The adoption of Generative AI (GenAI) in applications inevitably comes with the expansion of the attack surface, combining new security threats along with the traditional ones. Consequently, numerous research and industrial initiatives aim…

Neural networks are increasingly used to support decision-making. To verify their reliability and adaptability, researchers and practitioners have proposed a variety of tools and methods for tasks such as NN code verification, refactoring,…

Guardrail models (a.k.a. safety checkers) are widely deployed to screen user inputs before they reach large language models (LLMs), serving as a primary defense against prompt injection attacks. Due to strict context constraints, these…

Neural Networks (NNs) trained through supervised learning struggle with managing edge-case scenarios common in real-world driving due to the intractability of exhaustive datasets covering all edge-cases, making knowledge-driven approaches,…

Large Language Models (LLMs) are powerful tools for answering user queries, yet they remain highly vulnerable to jailbreak attacks. Existing guardrail methods typically rely on internal features or textual responses to detect malicious…

This position paper proposes a novel approach to advancing NLP security by leveraging Large Language Models (LLMs) as engines for generating diverse adversarial attacks. Building upon recent work demonstrating LLMs' effectiveness in…

Software engineers in various industrial domains are already using Large Language Models (LLMs) to accelerate the process of implementing parts of software systems. When considering its potential use for ADAS or AD systems in the automotive…

Recent advancements in large language models (LLMs) have notably propelled natural language processing (NLP) capabilities, demonstrating significant potential in safety engineering applications. Despite these advancements, LLMs face…

Guardrails are a critical safety layer for modern AI systems, but their operating regime is changing. As LLMs are deployed as customized assistants, safety policies are increasingly specified at inference time by users, organizations, or…

Improving and understanding the training dynamics and reasoning of Large Language Models (LLMs) has become essential for their deployment in AI-based security tools, such as software vulnerability detection. In this work, we present an…

Threat modeling is a crucial component of cybersecurity, particularly for industries such as banking, where the security of financial data is paramount. Traditional threat modeling approaches require expert intervention and manual effort,…

Retrieval-Augmented Generation (RAG) integrates Large Language Models (LLMs) with external knowledge bases, improving output quality while introducing new security risks. Existing studies on RAG vulnerabilities typically focus on exploiting…

Recent advancements in generative AI have enabled ubiquitous access to large language models (LLMs). Empowered by their exceptional capabilities to understand and generate human-like text, these models are being increasingly integrated into…

Large Language Models (LLMs) have recently shown promise as high-level planners for robots when given access to a selection of low-level skills. However, it is often assumed that LLMs do not possess sufficient knowledge to be used for the…

Mechanism design has long been a cornerstone of economic theory, with traditional approaches relying on mathematical derivations. Recently, automated approaches, including differentiable economics with neural networks, have emerged for…

Making LLMs speak for different, especially minority groups of people, and generate statements supporting their diverse or even controversial perspectives is critical to creating an inclusive environment. However, existing LLMs lack…

We propose a novel architecture for integrating large language models (LLMs) with a persistent, interactive Lisp environment. This setup enables LLMs to define, invoke, and evolve their own tools through programmatic interaction with a live…

How to best use Large Language Models (LLMs) for software engineering is covered in many publications in recent years. However, most of this work focuses on widely-used general purpose programming languages. The utility of LLMs for software…

We propose Modal Logical Neural Networks (MLNNs), a neurosymbolic framework that integrates deep learning with the formal semantics of modal logic, enabling reasoning about necessity and possibility. Drawing on Kripke semantics, we…

Large language models (LLMs) have recently been applied in software engineering to perform tasks such as translating code between programming languages, generating code from natural language, and autocompleting code as it is being written.…