Related papers: A Validated Prompt Bank for Malicious Code Generat…

Prompt-guided generative AI models have rapidly expanded across vision and language domains, producing realistic and diverse outputs from textual inputs. The growing variety of such models, trained with different data and architectures,…

AI governance programmes increasingly rely on natural language prompts to constrain and direct AI agent behaviour. These prompts function as executable specifications: they define the agent's mandate, scope, and quality criteria. Despite…

Evaluation of repository-aware software engineering systems is often confounded by synthetic task design, prompt leakage, and temporal contamination between repository knowledge and future code changes. We present a time-consistent…

Qualitative analysis plays a pivotal role in understanding the human and social aspects of software engineering. However, it remains a demanding process shaped by the subjective interpretation of individual researchers and sensitive to…

Pre-trained language models derive substantial linguistic and factual knowledge from the massive corpora on which they are trained, and prompt engineering seeks to align these models to specific tasks. Unfortunately, existing prompt…

The NPM ecosystem has become a primary target for software supply chain attacks, yet existing detection tools are evaluated in isolation on incompatible datasets, making cross-tool comparison unreliable. We conduct a benchmark-driven…

Bias audits of large language models now operate within governance frameworks such as the EU AI Act, making benchmark reliability a security concern in its own right. Many current benchmarks, however, collapse bias into a single scalar from…

Large Language Models (LLMs) are being increasingly integrated into software systems, offering powerful capabilities but also raising concerns about fairness. Existing fairness benchmarks, however, focus on stereotype-specific associations,…

Safety evaluations of large language models (LLMs) typically report binary outcomes, i.e. attack success rate (ASR), refusal rate, or harmful versus safe classification, which hide how risk changes between prompt and response. We present a…

We present and evaluate a suite of proof-of-concept (PoC), structured workflow prompts designed to elicit human-like hierarchical reasoning while guiding Large Language Models (LLMs) in the high-level semantic and linguistic analysis of…

Large Language Models (LLMs) require careful safety alignment to prevent malicious outputs. While significant research focuses on mitigating harmful content generation, the enhanced safety often come with the side effect of over-refusal,…

Motivated by undetectable risks in generative AI, we study a general robust aggregation problem: how to aggregate several probability distributions to boost safety. We present consensus sampling, a black-box algorithm that, given k…

This study investigates the reliability of code generation by Large Language Models (LLMs), focusing on identifying and analyzing defects in the generated code. Despite the advanced capabilities of LLMs in automating code generation,…

Federated learning enables clients to collaboratively learn a shared global model without sharing their local training data with a cloud server. However, malicious clients can corrupt the global model to predict incorrect labels for testing…

Fixed reasoning benchmarks evaluate canonical prompts, but semantically valid changes in presentation can still change model behavior. Studies of prompt variation can reveal such failures, but without audit they can mix genuine model errors…

Large language models (LLMs) are now widely used to draft and refactor code, but code that works is not necessarily secure. We evaluate secure code generation using the Instruct Prime, which eliminated compliance-required prompts and cue…

Large Language Models (LLMs) are gaining traction as a method to generate consensus statements and aggregate preferences in digital democracy experiments. Yet, LLMs could introduce critical vulnerabilities in these systems. Here, we examine…

The emergence of Large Language Models (LLMs) has significantly influenced various aspects of software development activities. Despite their benefits, LLMs also pose notable risks, including the potential to generate harmful content and…

When a user tells an AI system that someone "should not" take an action, the system ought to treat this as a prohibition. Yet many large language models do the opposite: they interpret negated instructions as affirmations. We audited 16…

Large language models often produce unsupported claims. We frame this as a misclassification error at the output boundary, where internally generated completions are emitted as if they were grounded in evidence. This motivates a composite…