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.
New preprints (not yet peer-reviewed)
Intent-Aware Protection for AI Agents
AI agents increasingly access enterprise data, invoke powerful tools, and act with limited human oversight. Existing security defenses primarily detect prompt injection, harmful outputs, or suspicious behavior, but do not determine whether an agent remains faithful to the purpose for which it was deployed.
From Delegation to Coordination: Learning Efficient Multi-Agent Deep Research
Multi-agent deep-research systems use delegation to parallelize search and keep long tool traces out of the main agent's context. Yet delegation helps only when task allocation and subtask execution are coordinated: the main agent must issue useful subtasks, while subagents must return reliable evidence.
Bait: Mitigating Harmful Agentic Reinforcement Learning via Probing Reward Function
We expose a safety vulnerability on nascent agentic reinforcement-learning-as-a-service. Specifically, with a cost as low as $20, we show that safety alignment of a large language model (e.g., Inkling) can be completely subverted through rounds of harmful agentic reinforcement learning (agentic RL) with a toxic environment from its users.
Specification-based Security Evaluation of Real-World Agents Tool-Calling under Long-Horizon Context Tasks
As large language model (LLM) agents are increasingly deployed in long-horizon unattended scenarios, security evaluation of them before deployment becomes increasingly essential and challenging. Existing evaluation methods mainly follow the paradigms of LLM-as-a-Judge or Agent-as-a-Judge.
CellularS2-Bench: A Staged, Evidence-Grounded Benchmark for Cellular Network Security Reasoning
Cellular networks are critical infrastructure supporting billions of worldwide users and safety- and mission-critical services. Vulnerabilities in cellular networks can therefore cause service disruption, privacy breaches, and broad societal harm, motivating growing efforts to analyze 3GPP specifications that define required device and operator behavior.
BELLS-O: Evaluating the Operational Trade-offs of LLM Supervision Systems
LLM supervision systems, namely input/output moderation filters and jailbreak detectors, are the primary safeguard against misuse in deployed AI applications, yet existing benchmarks are often vendor-biased, omit cost and latency, and rarely compare specialized guardrails against repurposed generalist LLMs. We present BELLS-O (Benchmark for the Evaluation of LLM Supervision Systems, Operational), an independent operational benchmark that evaluates 33 systems from 17 developers: specialized guardrails (e.g., Llama Guard 4, ShieldGemma-2B, Lakera Guard) and frontier generalists repurposed as supervisors (e.g., GPT-5.4, Claude Sonnet 4.6, Grok 4.1 Fast), jointly on detection rate, false-positive rate, latency, and cost.
SynthCorp: A Platform for Creating Benchmarks for Data Agents
Current benchmarks for LLM-driven data agents saturate quickly and cannot target specific capabilities. We present SynthCorp, a platform that creates customizable data estates and benchmarks by simulating how business events produce and modify corporate data over time.
Beyond the Diff – VulSpot: A Vulnerability Dataset Where No Vulnerability Goes Unlocalized
A vulnerability detector is only as trustworthy as the benchmark that scores it, and today's real-world datasets tend to flatter detectors. They are often built once and never refreshed, so they quickly miss new vulnerabilities, their labels are either noisy or heavily filtered, and their random splits let models train on near-copies of test code and on future vulnerabilities.
