Papers for

enterprise it operators

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

HazardAuditor improves safety for computer-use agents across platforms

HazardAuditor: From Executable Threats to Safer Computer-Use Agents

Abstract: Computer-use agents increasingly interact with browsers, terminals, file systems, and external services, introducing safety risks that emerge through runtime behavior rather than generated content alone. Existing guard models target static prompts and responses and are poorly suited to agent execution; existing executable safety platforms produce evaluation verdicts rather than the normalized supervision a guard model needs to learn across heterogeneous agent frameworks. We introduce HazardAuditor, an execution-grounded framework that closes both gaps. Its infrastructure runs heterogeneous agents (Claude Code, Codex, Hermes, and OpenClaw) in controlled environments and normalizes their interactions into a canonical event representation for cross-framework supervision. We further observe that token-level post-training objectives create a structural mismatch for generative guards, causing longer rationales to dominate gradient updates. Guard Policy Optimization (GuardPO) addresses this by converting deterministic safety outcomes into sequence-level advantages and normalizing rationale and verdict regions, making the safety decision the effective unit of optimization. Across multiple benchmarks and heterogeneous computer-use systems, HazardAuditor improves accuracy by up to 16.5 percentage points over the strongest prior guard. Code, models, and evaluation artifacts will be available at https://yunhao-feng.github.io/HazardAuditor/.

Mon 14 SeptArtificial Intelligence
The gist
Computer-use agents that interact with software like browsers and terminals can sometimes behave unsafely at runtime, which is hard to detect. The authors present HazardAuditor, a system that runs different agents in controlled setups and standardizes their actions to better supervise safety. They also introduce a method called Guard Policy Optimization to improve how safety decisions are learned, focusing on the final safety outcomes rather than long explanations. Their approach improves accuracy in identifying unsafe behaviors across various agent frameworks.
Open 2609.15134v1

Windows malware detection balance accuracy speed and attacker defense

Windows Malware Detector as a Compound AI System: Trade-Offs in Accuracy, Efficiency, and Adversarial Robustness

Abstract: Industrial Windows malware detectors are commonly described as Compound AI Systems composed of multiple heterogeneous components, including rule-based mechanisms as well as machine-learning-based static and dynamic analyses. However, due to industrial secrecy and limited public disclosure, the internal architectures of these systems can only be inferred, rendering systematic evaluations of detection accuracy, computational costs, and adversarial robustness largely infeasible. In contrast, academic research provides reproducible and transparent evaluation methodologies, but typically investigates individual detection components in isolation. To bridge the gap between academic research and industrial practice, and inspired by state-of-the-art industrial architectures for Windows malware detection, we propose a novel methodology that (i) explicitly balances the trade-off among detection performance, computational requirements, and robustness, and introduces (ii) system-level threat models that capture how attackers exploit different degrees of knowledge to evade the entire Compound AI System rather than isolated detectors. Experiments conducted on real-world data demonstrate that the Compound AI System training time can be reduced and responsiveness improved while incurring only a marginal loss in detection performance. Leveraging our threat modeling, we show that increasingly knowledgeable attackers craft more effective adversarial examples, revealing the system's strengths and weaknesses, degrading its responsiveness, and exposing a direct trade-off between efficiency and robustness. Finally, we translate these trade-offs into take-home messages and deployment guidelines, helping practitioners to select the system that best matches their operational constraints.

Tue 8 SeptCryptography and Security
The gist
Detecting harmful software on Windows often uses many different tools combined to catch bad programs effectively. The authors created a way to measure how well these combined tools work, how fast they operate, and how well they resist attackers trying to fool them. They tested this approach on real data, showing that training can be faster and the system more responsive while still detecting most threats. They also found that smarter attackers can trick the system more easily, showing a balance between making the system quick and making it hard to attack.
Open 2609.08394v1