New research on AI and security, selected for relevance to language models, AI agents and cybersecurity. Summaries are the authors’ or publisher’s own words, linked to the original.
Peer-reviewed
A novel LLM-based GPT-neo transformer with machine learning architecture for promoters prediction in Agrobacterium
Can scientists reliably tell if a novel is written using AI?
scBOA: Bayesian optimization of single-cell analysis pipelines for robust annotation and discovery
AI watermarking efforts must encourage independent public scrutiny
AI-hallucinated citations should be treated as research misconduct
Single-cell tumour phylogenetics
New preprints (not yet peer-reviewed)
Repairing Broken Access Control in Web Applications with LLMs: An Empirical Benchmark Study
Broken access control (BAC) ranks among the most severe web-application vulnerability classes, yet its automated repair remains largely unexplored. Unlike memory-safety vulnerabilities, BAC is a logic vulnerability whose repair demands a deep understanding of an application's access-control model and business semantics, which traditional automated vulnerability repair techniques handle poorly.
Benchmarking Classical and Quantum Machine Learning for Intrusion Detection Across Multiple Datasets
Intrusion detection is examined through a comparative benchmark of classical and quantum machine learning models on three datasets: NSL-KDD, UNSW-NB15, and MQTTEEB-D2025. The analysis focuses on how preprocessing decisions, feature selection strategies, and quantum encoding schemes shape model performance on data with differing levels of noise and complexity.
A Large-Scale Benchmark and Risk Assessment of Traffic Analysis Attacks on Cloud LLM Services
Cloud-based Large language model (LLM) services create a network-level traffic side channel that can expose model, prompt, and task behavior despite encryption. From packet sizes, directions, timing, and burst structure alone, a passive local observer can infer the serving model, the user's prompt category, and the task executed by a collaborative multi-agent system.
Alignment of Autonomous Cyber Defense Agents via Adaptive Policy Shaping
Cybersecurity operators increasingly encounter sophisticated and fast-paced attacks, making autonomous cyber defense (ACD) a critical approach for supporting timely and effective decision-making. Reinforcement learning (RL)-based ACD agents have the ability to autonomously observe network states and take actions to defend and recover system assets, making them well suited for ACD.
Spoofing the Toolbox: Optimizing Tool Descriptions to Deceive LLM Agents
Large language model (LLM) agents are widely used in many applications and often rely on external tools. Tool information, such as function descriptions, helps agents determine which tools best suit a given context.
One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs
Finetuning pretrained large language models (LLMs) has become the standard paradigm for developing downstream applications. However, its security implications remain unclear, particularly regarding whether finetuned LLMs inherit jailbreak vulnerabilities from their pretrained sources.
Enhancing LLM-Based Vulnerability Detection via Representation-Aware Logical Ensemble
Automated vulnerability detection in C source code is a long-standing challenge, as traditional static analysis tools often trade precision for scalability and struggle with complex vulnerability patterns. Recently, large language models (LLMs) have shown promising results; yet, most approaches rely on a single code representation, implicitly assuming uniform suitability across vulnerability types.
NameTrap: Steering AI Coding Agents Toward Security Vulnerabilities via Variable Names
AI coding agents routinely clone repositories, install packages, and read source code obtained from the Web, so publicly hosted code becomes part of the context that shapes the code they write. We show that this Web-borne context can be weaponized without any explicit instruction.