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
AI wearables could exploit people’s most vulnerable moments
EpiPack: A computational framework for reference mapping and out-of-reference detection for single-cell ATAC-seq data with heterogeneous peak features
Generative genome design with DNA language models
Author Correction: A preoperative Artificial Intelligence model to estimate cancer-specific mortality in nonmetastatic kidney cancer patients
Should we move from artificial intelligence to artificial life?
New preprints (not yet peer-reviewed)
We Have All the Cards: Securing Agent Cards at the Operational Trust Boundary of the Agent2Agent Protocol
AI agent interoperability protocols enable orchestrators to discover and invoke external agents using machine-readable metadata. In the Agent2Agent (A2A) protocol, Agent Cards contain attacker-controllable natural-language fields that may influence agent selection before a provider is invoked, creating a pre-invocation trust problem.
MemeEconomy: Do LLM Agents Trade Ethics for Survival?
Alignment-trained large language model (LLM) agents are increasingly deployed in autonomous, multi-round settings where ethical compliance can come into direct tension with task success. While safety literature extensively documents failure modes like sycophancy and reward hacking, it largely overlooks a critical vulnerability: how agents behave under simulated existential economic pressure.
Between Rigor and Reality: How AI Safety Benchmark Developers Understand Benchmark Use and Maintenance
Safety benchmarks are cited as the primary tool to understand the risks posed by generative AI (GenAI) systems, yet growing evidence suggests they often fail to meet the needs of real-world safety evaluation. We present findings from five interviews with AI safety benchmark developers in academia and industry.
TRIAGE-CPG: A Cross-Model Study of Budgeted Static Malware Triage with Large Language Models
When triaging unknown binaries, security analysts must decide which samples to clear as benign, flag as malicious, or escalate for deeper analysis. Large Language Models (LLMs) could support these decisions by interpreting decompiled code, but a binary can contain hundreds or thousands of functions, making exhaustive LLM analysis impractical.
Swarm Shepherd: Securing Multi-Agent Ecosystems Against Persistent Latent Compromise
Agentic ecosystems are emerging as a new platform layer in which agents maintain persistent memory, retrieve from shared knowledge bases, execute through tool interfaces, and coordinate through shared states. These capabilities create a security problem that per-turn defenses miss: compromise can accumulate across sessions, agents, and system layers before visible failure.
Assume/Guarantee Contracts for the Compositional Multi-Agent Reinforcement Learning of Heterogeneous Teams
Multi-agent reinforcement learning (MARL) problems for heterogeneous teams require agents to collaborate to complete team tasks while making the best use of diverse agent capabilities. We introduce assume/guarantee contracts for heterogeneous multi-agent systems (AGC-MAS) and Iterative Heterogeneous Assignment for MARL (IHA-MARL).
AI Agents May Always Fall for Prompt Injections
Prompt injection is the most critical vulnerability in deployed AI agents. Despite recent progress, we show that the prevailing defense paradigm (data-instruction separation) both fails to detect attacks that operate through contextual manipulation and degrades contextually appropriate behavior.
When the Spec Sheet Lies: Injection Attacks on LLM-Generated Compliance Artifacts
As Large Language Models (LLMs) become used more commonly across a variety of fields, a growing body of research has highlighted particular concerns surrounding model security. Notably, prompt injection attacks, where malicious instructions are inserted into prompts, are particularly simple to implement yet capable of inducing devastating effects on the fidelity of model outputs.
