arXiv subjects

Shaun Ee

Publications and source records attributed to Shaun Ee.

6 recordsLinked to original sources

arXiv2026

Detecting Offensive Cyber Agents: A Detection-in-Depth Approach

Artificial Intelligence (AI) agents can now orchestrate cyberattacks. This development is already increasing the speed and scale of cyber attacks, decreasing attack costs, and improving the operational autonomy of cyber capabilities. To defend against these emerging threats, actors must first develop the capability to detect them. This report frames the offensive cyber agent detection challenge by outlining the coming detection gap between offensive cyber agents and traditional cyber capabilities; introducing detection-in-depth, a strategic framework to guide policymakers and defenders responding to this detection gap; and presents five actionable detection mechanisms to support policymakers, industry, and defenders when putting this strategic framework into practice. These include (1) Agent Identifiers for Critical Infrastructure,(2) Agent Honeypots; (3) AI-Automated Alert Analysis and Triage: systems that use AI to filter, prioritize, and interpret the growing volume of detection signals expected from autonomous cyber operations; (4) An Agentic Security Alert Standard: A reporting standard model that providers can use to communicate agentic threats, improving the speed, consistency, and actionability of reports; (5) An Agentic Cybersecurity Exchange (ACE): an institution modeled on the Global Signal Exchange that brings together model and cloud providers to detect offensive cyber agent threats at their origin point and coordinate ecosystem-wide agentic threat disruption.

cs.CY↗

arXiv2026

Highly Autonomous Cyber-Capable Agents: Anticipating Capabilities, Tactics, and Strategic Implications

This report introduces the concept of "Highly Autonomous Cyber-Capable Agents" (HACCAs), AI systems capable of autonomously conducting multi-stage cyber campaigns at a level comparable to today's top criminal hacking groups or state-affiliated threat actors, and analyzes the security implications of their emergence. The report: (1) Defines what HACCAs are and forecasts when they might arrive, establishing a clear framework for an autonomous cyber agent that can operate across the full attack lifecycle without meaningful human direction; (2) Identifies five core operational tactics, detailing how HACCAs could sustain themselves in the wild, from autonomous infrastructure setup and credential harvesting to detection evasion and adaptive shutdown avoidance; (3) Analyzes the strategic implications, including how HACCAs could intensify interstate cyber competition, lower the barrier to entry for sophisticated operations, and proliferate advanced offensive capabilities to criminal groups and less-resourced state actors; (4) Flags two tail risks that deserve serious attention: the potential for autonomous cyber operations to trigger inadvertent cyber-nuclear escalation, and the possibility of sustained loss of control over rogue HACCA deployments; (5) Proposes seven policy recommendations across three goals: understanding the emerging threat, defending against HACCAs, and ensuring their responsible development and deployment.

cs.CY↗

arXiv2025

Asymmetry by Design: Boosting Cyber Defenders with Differential Access to AI

As AI-enabled cyber capabilities become more advanced, we propose "differential access" as a strategy to tilt the cybersecurity balance toward defense by shaping access to these capabilities. We introduce three possible approaches that form a continuum, becoming progressively more restrictive for higher-risk capabilities: Promote Access, Manage Access, and Deny by Default. However, a key principle across all approaches is the need to prioritize defender access, even in the most restrictive scenarios, so that defenders can prepare for adversaries gaining access to similar capabilities. This report provides a process to help frontier AI developers choose and implement one of the three differential access approaches, including considerations based on a model's cyber capabilities, a defender's maturity and role, and strategic and technical implementation details. We also present four example schemes for defenders to reference, demonstrating how differential access provides value across various capability and defender levels, and suggest directions for further research.

cs.CR↗

arXiv2024

Adapting cybersecurity frameworks to manage frontier AI risks: A defense-in-depth approach

The complex and evolving threat landscape of frontier AI development requires a multi-layered approach to risk management ("defense-in-depth"). By reviewing cybersecurity and AI frameworks, we outline three approaches that can help identify gaps in the management of AI-related risks. First, a functional approach identifies essential categories of activities ("functions") that a risk management approach should cover, as in the NIST Cybersecurity Framework (CSF) and AI Risk Management Framework (AI RMF). Second, a lifecycle approach instead assigns safety and security activities across the model development lifecycle, as in DevSecOps and the OECD AI lifecycle framework. Third, a threat-based approach identifies tactics, techniques, and procedures (TTPs) used by malicious actors, as in the MITRE ATT&CK and MITRE ATLAS databases. We recommend that frontier AI developers and policymakers begin by adopting the functional approach, given the existence of the NIST AI RMF and other supplementary guides, but also establish a detailed frontier AI lifecycle model and threat-based TTP databases for future use.

cs.CY↗

arXiv2024

Coordinated Disclosure of Dual-Use Capabilities: An Early Warning System for Advanced AI

Advanced AI systems may be developed which exhibit capabilities that present significant risks to public safety or security. They may also exhibit capabilities that may be applied defensively in a wide set of domains, including (but not limited to) developing societal resilience against AI threats. We propose Coordinated Disclosure of Dual-Use Capabilities (CDDC) as a process to guide early information-sharing between advanced AI developers, US government agencies, and other private sector actors about these capabilities. The process centers around an information clearinghouse (the "coordinator") which receives evidence of dual-use capabilities from finders via mandatory and/or voluntary reporting pathways, and passes noteworthy reports to defenders for follow-up (i.e., further analysis and response). This aims to provide the US government, dual-use foundation model developers, and other actors with an overview of AI capabilities that could significantly impact public safety and security, as well as maximal time to respond.

cs.CY↗

arXiv2023

Deployment Corrections: An incident response framework for frontier AI models

A comprehensive approach to addressing catastrophic risks from AI models should cover the full model lifecycle. This paper explores contingency plans for cases where pre-deployment risk management falls short: where either very dangerous models are deployed, or deployed models become very dangerous. Informed by incident response practices from industries including cybersecurity, we describe a toolkit of deployment corrections that AI developers can use to respond to dangerous capabilities, behaviors, or use cases of AI models that develop or are detected after deployment. We also provide a framework for AI developers to prepare and implement this toolkit. We conclude by recommending that frontier AI developers should (1) maintain control over model access, (2) establish or grow dedicated teams to design and maintain processes for deployment corrections, including incident response plans, and (3) establish these deployment corrections as allowable actions with downstream users. We also recommend frontier AI developers, standard-setting organizations, and regulators should collaborate to define a standardized industry-wide approach to the use of deployment corrections in incident response. Caveat: This work applies to frontier AI models that are made available through interfaces (e.g., API) that provide the AI developer or another upstream party means of maintaining control over access (e.g., GPT-4 or Claude). It does not apply to management of catastrophic risk from open-source models (e.g., BLOOM or Llama-2), for which the restrictions we discuss are largely unenforceable.

cs.CY↗