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 document classification benchmark dataset on cybersecurity policy domain
DSIN: dynamic system-empowered implicit neural representation for medical image compression
Limitations of de novo peptide sequencing in resolving sequence ambiguity
Universities must measure learning, both with and without AI assistance
Genome-anchored foundation model embeddings improve molecular prediction from histology images
Building a pre-trained model for single-cell multi-omics analysis beyond highly variable feature selection
New preprints (not yet peer-reviewed)
MAS-Guard: Unified Guardrails from Individual Agents to Multi-Agent LLM Systems
Agentic AI extends large language models (LLMs) from generating responses to planning and executing complex workflows, substantially expanding their utility while exposing applications to unsafe actions, information leakage, and adversarial manipulation. Multi-agent systems further expand these capabilities through specialization and collaboration, but distributed authority, heterogeneous roles, and opaque or potentially compromised participants make safeguarding even more challenging.
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.
AgentCap: Capability-Based Runtime Authorization for Secure LLM Agent Execution
Language-model agents commonly collapse two decisions that security systems separate: selecting an action and determining whether that action is authorized. When a model exercises standing authority, indirect prompt injection can convert influence over its reasoning into unauthorized effects.
AgentTypo: Adaptive Typographic Prompt Injection Attacks against Black-box Multimodal Agents
Multimodal agents built on large vision-language models are increasingly deployed in open-world settings but remain highly vulnerable to prompt injection. Typographic text-in-image attacks such as FigStep have been evaluated mainly on standalone vision-language models.
Do Agents Still Follow the Rules? Benchmarking Rule Compliance under Agent Context Compaction
LLM agents compact long histories to fit their context windows, but the compacted context must still carry the operating rules that govern later actions. Prior work shows that violations rise after compaction, but measures compliance outside a complete agent harness and does not identify where each violation comes from.
How Safe Are AI-Generated Patches? A Large-scale Study on Security Risks in LLM and Agentic Automated Program Repair on SWE-bench
Large language models (LLMs) and agentic frameworks are increasingly used for development tasks such as automated program repair (APR). Prior work has identified security risks in LLM-generated code, but most studies focus on synthetic, simplified, or isolated tasks.
Decentralized Multi-Agent Coordination and Communication in Shared Codebases
Coding agents working in shared repositories may receive separate, independently-motivated requests from human developers, creating a setting that is multi-agent by necessity. When this scenario happens, their individual implementations may work separately but conflict when combined.
Systematic Evaluation of Adversarial Jailbreaking Attacks and Defenses Across Seven Large Language Models
Large language models (LLMs) deployed in safety-critical settings must resist adversarial inputs designed to elicit harmful outputs. We present a systematic empirical evaluation of five adversarial jailbreaking attack families—direct requests, roleplay-based jailbreaking, hypothetical framing, instruction override, and obfuscation—across seven open-weight LLMs served locally: Llama-3-8B, Llama-3.1-8B, Llama-3.2-3B, Mistral-7B, Qwen2.5-7B, Gemma2-9B, and Phi-4-14B.