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
An all-in-one foundation model for multimodal medical image restoration and enhancement
China’s AI research is booming. Where is it headed?
China’s AI research is booming. Where is it headed?
Is this idea from AI or humans? A detector claims it can tell
NiCLIP: neuroimaging contrastive language-image pretraining model for predicting text from brain activation images
Preserve research data for tomorrow’s AI-enabled integrity checks
New preprints (not yet peer-reviewed)
VulnBump: A Benchmark for Fixing Vulnerable Dependencies in Real Projects While Keeping the Build and Tests Green
Software composition analysis (SCA) tools report far more vulnerable dependencies than teams fix: in Snyk Open Source production data, 94% of vulnerability findings have a known fixed version, yet only about 10% are resolved. Agentic coding tools could close this gap, but no benchmark evaluates them on vulnerability-driven upgrades in real, runnable projects across ecosystems, verified independently of the agent.
Natural Code Transformation Confuses Agents in Vulnerability Analysis
Having demonstrated a strong potential for automating vulnerability discovery, AI agents can also be used to attack software systems at scale. Today's software systems need mechanisms to level the playing field by slowing down potential attacks, giving them time to patch vulnerabilities and strengthen software.
Are Multimodal Benchmarks Really Useful? Item-Level Multimodal Benchmark Diagnosis via Structure-Response Co-Calibration
Multimodal benchmarks are central to evaluating whether models can reason over information from multiple modalities. However, existing literature has revealed that some benchmarks may contain shortcut items that can be answered from a single modality or from answer-option regularities alone, thus failing to reflect models' true cross-modal inference ability.
Constitutional Gating and Deterministic Recovery for Multi-Agent LLM Negotiation: Ablations Against a Stateful Adversarial Gatekeeper
Multi-agent LLM systems negotiating with a stateful counterpart waste model calls in three ways: polite loops that never meet the counterpart's hidden acceptance condition, malformed outputs that trigger retries, and compliance deadlocks in which the counterpart demands something the agent must refuse. We study a three-part control stack – a 5-Pillar runtime constitution, a 4-tier swarm (Director, three-agent majority vote, Monitor, schema hard gate) and Cognitive Annealing (deterministic deadlock detection, atomic purge of the agent-side context, a canonical recovery message) – against a released adversarial Gatekeeper whose acceptance rules are fixed regular expressions and whose LLM only renders reply text.
ClawLoop: Self-Improving Agents via Harness-Native Training Loop
The rapid advancement of Large Language Models (LLMs) has driven their deployment toward general-purpose harness environments, where LLM-based agents operate in sandbox workspaces and interact directly with file systems and shells. While numerous post-training pipelines exist for tool-use agents, their counterparts for harness-based agents remain scarce and are predominantly one-shot and teacher-dependent: a stronger external model synthesizes tasks and collects trajectories, the target agent is trained once, and evaluation results are consumed by human researchers rather than fed back into the loop.
NeuroFilter: Activation-Based Guardrails for Privacy-Conscious LLM Agents
Agentic Large Language Models (LLMs) are models able to reason, plan, and execute tools over unstructured data. These abilities enable transformative applications in domains spanning personal assistants, financial, and legal domains, etc.
Protecting Shared Agent Workflows from Invalidation Attacks with Signed Trajectories and Runtime Verification
Large language model (LLM)-based agents increasingly rely on shared workflow repositories to transfer experience across tasks and agents. By abstracting past executions into reusable workflow graphs, such systems significantly improve planning efficiency and generalization.
Measuring LLM Agent Defenses by Layer: GDA Measurement and an Envelope-Layer Attack-Defense Model
Agent interaction protocols such as ACP and A2A let a remote peer deliver a task the receiving agent treats as legitimate, opening a channel for indirect prompt injection. Evaluating and defending such agents is difficult because the attack success rate (ASR) cannot distinguish an LLM recognition failure from an agent-layer block, and so cannot indicate which layer to strengthen.