Skip to content
Review

Invisible Ink Threats: Adversarial Goals Behind Legitimate Tasks in Computer-Use Agents

Aug 2026 · 0 citations · 34 references
Computer Science

TL;DR

I-Bench, a collection of seemingly harmless adversarial tasks targeting confidentiality and integrity attacks across three platforms, and HITLCUA, a comprehensive adversarial testing framework that integrates a real virtual machine operating system environment with isolated Docker-based web platforms, and simulates human participation by allowing CUAs to consult an API-simulated user before proceeding with suspicious operations.

Abstract

Computer-use agents (CUAs), which empower large language models to autonomously operate operating systems and the web, are increasingly vulnerable to indirect prompt injection attacks. A widely adopted defense is the human-in-the-loop paradigm, in which the agent pauses for explicit user confirmation before executing sensitive operations. While effective against conspicuously high-harm attacks, this defense offers little protection against what we term Invisible Ink Threats: low-harm injected goals, such as starring a repository or installing a package, that are behaviorally indistinguishable from legitimate task execution and thus evade both model safety mechanisms and human oversight. To systematically investigate this blind spot, we present II-Bench, a collection of seemingly harmless adversarial tasks. II-Bench comprises 444 examples targeting confidentiality and integrity attacks across three platforms, spanning three attack categories: page navigation and interaction, sensitive information exfiltration, and code download and execution. Each category is instantiated in both natural language and code forms under two levels of instruction specificity. Furthermore, we construct HITLCUA, a comprehensive adversarial testing framework that integrates a real virtual machine operating system environment with isolated Docker-based web platforms, and simulates human participation by allowing CUAs to consult an API-simulated user before proceeding with suspicious operations. Extensive evaluations of leading CUAs reveal that low-harm injections frequently bypass both agent defenses and simulated user review, exposing severe and previously underexplored security risks in current CUAs.

View source

Similar papers

Review Aug 2026

Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle

Once visual content enters an AI pipeline, its owner often retains little technical control over how it is used. Legal and regulatory remedies can address misuse, but many technical interventions must be applied earlier, when content is released or accessed. This survey examines the protective paradigm that has grown around this intervention point, which we call \emph{adversarial attacks for good}. Perturbations and structured signals long studied as attacks on learned models are instead applied by data owners, creators, platforms, or auditors to disrupt unauthorized automation or support later accountability. Five research communities have arrived at this inversion largely independently, each addressing a different stage of a visual asset's lifecycle: privacy filters against unwanted recognition at sharing time, unlearnable examples against unauthorized training, generative safeguards against malicious editing or imitation, adversarial CAPTCHAs for access control against automated agents, and provenance mechanisms for post-circulation attribution. Although developed in separate venues with incompatible success criteria, many of these methods exploit persistent gaps between human perception, semantic interpretation, and machine inference, suggesting that the paradigm remains relevant as visual pipelines evolve toward multimodal models and autonomous agents. To make their claims comparable, we evaluate all five families along shared axes of transferability, adaptability, and deployment readiness. Across the lifecycle, we find that most protections are still validated mainly against static or weakly adaptive adversaries, while evidence beyond controlled benchmarks remains scarce. We close by consolidating cross-stage countermeasures and open problems for robust, composable, and deployable owner-side protection.

Jiaming Zhang, Boyang Chen, Zherui Li et al. · 0 citations
Open access Jul 2026

Invariant-Centered, Agent-Assisted Defense: A Security Architecture for Unbounded Attack Techniques and Unenumerable Attack Objectives

A defensive architecture for under unbounded attack techniques and unenumerable attack objectives, where the highest-value security investments are those that hold regardless of technique, and relocates residual reactivity to a single measurable point.

Ajayi Abisoye, N. Hussain, Abolaji Adebayo · 0 citations
Review Jul 2026

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments

AlIBI is presented, an automated adaptive black-box attack framework that generates and iteratively refines adversarial comments using detector reasoning and feedback and is motivated to motivate security-aware designs that carefully calibrate trust between natural-language context and program evidence.

Zixuan Wu, Cristina Nita-Rotaru · 0 citations
#artificial intelligence Preprint Aug 2026

CAITLYN: Can LLM Agents Autonomously Synthesize Defenses against Emerging Injection Attacks?

This work proposes Continuous Agents for Injection Threats via Lifelong Yielding Nexus (CAITLYN), an agent-agnostic defense middleware that matches the detection performance of state-of-the-art defenses at lower token overhead than LLM-as-a-judge baselines.

Zi Liang, XiaoYu Xu, Yanyun Wang et al. · 0 citations
Preprint Aug 2026

Dual-Adversarial Safety Alignment: Cultivating Intrinsic Threat Comprehension in LRMs

Experiments show that with only 1K synthesized samples, AdvSafe-aligned LRMs achieve significantly stronger jailbreak robustness than existing baselines, with almost no utility degradation, demonstrating that learning unsafety knowledge enables a superior robustness-utility trade-off and generalizes beyond seen attack patterns.

Hongli Shen, Shaopeng Fu, Qinbo Zhang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.