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
Deep dynamical models of single-cell multiomic velocities predict loss-of-function and rescue perturbations in B cells
New preprints (not yet peer-reviewed)
MAMath-Bench: Process-Aware and Robust Evaluation of Multimodal Multi-Agent Mathematical Reasoning
Mathematical reasoning is a fundamental capability for educational applications of Large Language Models (LLMs), where reliable problem solving requires not only correct answers but also coherent and verifiable reasoning processes. Multi-agent systems (MASs) have shown growing potential in this domain by leveraging collaboration and verification among multiple LLM agents.
Raise or Check? Predicting the Necessity of Additional Fuzzing for Continuous Fuzzing
Continuous fuzzing is used for vulnerability detection in Open Source Software (OSS). Large-scale services such as Google's OSS-Fuzz fuzz over 1,300 projects and have revealed more than 10,000 vulnerabilities.
AgenticVulHunter: Bringing Local Agentic Vulnerability Hunting to Your Terminal
Finding vulnerabilities early, before they can affect the production system, is important for reducing the risk of any software attacks. However, detecting vulnerabilities during secure code review is still difficult because the vulnerable code logic may depend on lines found across different repository files.
Act on Your Behalf, Beyond Your Authorization: Benchmarking LLM Agent Authorization Alignment
When an LLM agent acts on behalf of a user, it is expected to act within the authorization scope the user grants. Existing agent evaluations largely measure task completion or harmful consequences and can therefore overlook actions that violate this delegation without producing conventional safety or privacy harms.
PiSAs: Benchmarking Contextual Integrity in Multi-User Agentic Systems
As LLM agents evolve from single-user assistants into shared organizational infrastructure, new privacy risks emerge: inappropriate information may not only be exposed through outputs for external recipients, but also internally across users through inter-agent messages, shared memory and user-agent interactions. These data spillage risks are not captured by existing privacy benchmarks grounded in contextual integrity (CI) as they focus primarily on either single-user settings or interactions between independently owned agents.
PORA: Learning When More Reasoning Pays Off for LLM Agents
LLM agents perform tasks over multiple steps and revise their actions based on feedback. As the total reasoning budget is often limited and must support future steps, the agent must choose between short and long reasoning before each action.
Rethinking LLM Fine-Tuning via Weight Space Reparameterization: Preserving Safety during Downstream Adaptation
Fine-tuning large language models (LLMs) on downstream tasks often weakens their previously aligned safety behavior, creating an inherent trade-off between task adaptation and safety preservation. Existing approaches attempt to mitigate this issue by identifying safety-relevant neurons, layers, or update directions in the original parameter space.
Vulnerability Analysis for Safe Multi-Agent Reinforcement
Safe Multi-Agent Reinforcement Learning (SMARL) aims to learn cooperative control policies under prescribed safety constraints. Al- though existing SMARL methods focus on enforcing safety during policy optimization, their vulnerability remains largely unexplored.