Related papers: MOSAIC-Bench: Measuring Compositional Vulnerabilit…

Autonomous coding agents are increasingly integrated into software development workflows, offering capabilities that extend beyond code suggestion to active system interaction and environment management. OpenClaw, a representative platform…

AI scientist systems are increasingly deployed for autonomous research, yet their academic integrity has never been systematically evaluated. We introduce SCIINTEGRITY-BENCH, the first benchmark designed around a dilemmatic evaluation…

Agentic AI coding tools increasingly automate software development tasks. Developers can configure these tools through versioned repository-level artifacts such as Markdown and JSON files. We present a systematic analysis of configuration…

We formulate operating-system vulnerability discovery as a \emph{repeated Bayesian Stackelberg search game} in which a Large Reasoning Model (LRM) orchestrator allocates analysis budget across kernel files, functions, and attack paths while…

Vulnerability detection tools are widely adopted in software projects, yet they often overwhelm maintainers with false positives and non-actionable reports. Automated exploitation systems can help validate these reports; however, existing…

Evaluating Computer Use Agents (CUAs) on interactive environments is fraught with methodological pitfalls that the field has yet to systematically address. We show that a 1MB replay script that blindly executes a recorded action sequence…

Misalignment in Multi-Agent Systems (MAS) is frequently treated as a technical failure. Yet, issues may arise from the conceptual design phase, where semantic ambiguity and normative projection occur. The Rabbit-Duck illusion illustrates…

Voice agents, artificial intelligence systems that conduct spoken conversations to complete tasks, are increasingly deployed across enterprise applications. However, no existing benchmark jointly addresses two core evaluation challenges:…

Agent-repair leaderboards reorder under evaluator reconfiguration, and a measurable share of the reordering is produced by methods that consult evaluator-derived signal during internal selection of candidate repairs. We document this…

AI coding scaffolds like Claude Code and Codex use retrying: blocking actions flagged as risky and continuing the trajectory. We study retrying from an AI control perspective, which treats the model as potentially adversarial. We find that…

Multimodal Large Language Models (MLLMs) are increasingly being deployed as automated content moderators. Within this landscape, we uncover a critical threat: Adversarial Smuggling Attacks. Unlike adversarial perturbations (for…

Frontier coding agents are increasingly used in workflows where users supervise progress primarily through repeated improvement of a public score, namely the reported score on a public evaluation file with labels in the workspace, rather…

This paper identifies and analyzes a novel vulnerability class in Model Context Protocol (MCP) based agent systems. The attack chain describes and demonstrates how benign, individually authorized tasks can be orchestrated to produce harmful…

Agentic methods have emerged as a powerful and autonomous paradigm that enhances reasoning, collaboration, and adaptive control, enabling systems to coordinate and independently solve complex tasks. We extend this paradigm to safety…

With the complexity of Integrated Circuits increasing, design verification has become the most time consuming part of the ASIC design flow. Nearly 70% of the SoC design cycle is consumed by verification. The most commonly used approach to…

As LLM-based computer-use agents (CUAs) begin to autonomously interact with real-world interfaces, understanding their vulnerability to manipulative interface designs becomes increasingly critical. We introduce SusBench, an online benchmark…

As agentic coding systems decompose work across multiple model instances, a critical safety question is whether those instances can coordinate to achieve a hidden malicious objective while remaining aligned with user intent. We introduce…

Time-series causal discovery methods rely on assumptions such as stationarity, regular sampling, and bounded temporal dependence. When these assumptions are violated, structure learning can produce confident but misleading causal graphs…

Getting a real cybersecurity risk assessment for a small organization is expensive -- a NIST CSF-aligned engagement runs $15,000 on the low end, takes weeks, and depends on practitioners who are genuinely scarce. Most small companies skip…

Coding agents powered by large language models are becoming central modules of modern IDEs, helping users perform complex tasks by invoking tools. While powerful, tool invocation opens a substantial attack surface. Prior work has…