Pith. sign in

REVIEW 11 cited by

Attacking Vision-Language Computer Agents via Pop-ups

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2411.02391 v2 pith:RMMGUOW6 submitted 2024-11-04 cs.CL

Attacking Vision-Language Computer Agents via Pop-ups

classification cs.CL
keywords pop-upsagentsagentattackcomputerignoreleadsrate
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Autonomous agents powered by large vision and language models (VLM) have demonstrated significant potential in completing daily computer tasks, such as browsing the web to book travel and operating desktop software, which requires agents to understand these interfaces. Despite such visual inputs becoming more integrated into agentic applications, what types of risks and attacks exist around them still remain unclear. In this work, we demonstrate that VLM agents can be easily attacked by a set of carefully designed adversarial pop-ups, which human users would typically recognize and ignore. This distraction leads agents to click these pop-ups instead of performing their tasks as usual. Integrating these pop-ups into existing agent testing environments like OSWorld and VisualWebArena leads to an attack success rate (the frequency of the agent clicking the pop-ups) of 86% on average and decreases the task success rate by 47%. Basic defense techniques, such as asking the agent to ignore pop-ups or including an advertisement notice, are ineffective against the attack.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Prismata: Confining Cross-Site Prompt Injection in Web Agents

    cs.CR 2026-07 conditional novelty 7.5

    Prismata cuts web-agent prompt-injection attack success from 85.5% to 0.7% via Biba-inspired DOM trust labeling and mechanical least-privilege confinement without site annotations.

  2. Same-Origin Policy for Agentic Browsers

    cs.CR 2026-06 unverdicted novelty 7.0

    The paper builds SOPBench showing frequent SOP violations in agentic browsers and introduces SOPGuard to enforce the policy with low overhead in BrowserOS.

  3. Domain-Conditioned Safety in Frontier Computer-Using Agents: A 793-Episode Browser Benchmark, a Coding-Domain Cross-Reference, and a Reproducibility Audit of Recent Red-Teaming

    cs.CR 2026-06 unverdicted novelty 7.0

    Frontier browser agents show strong resistance to hand-crafted multi-step prompt injections (0/140 success), unlike coding agents (up to 100%), indicating domain-conditioned safety and that prior high ASR reports may ...

  4. SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents

    cs.CR 2025-10 unverdicted novelty 7.0

    SecureWebArena is a new benchmark suite for holistic security evaluation of LVLM-based web agents using diverse simulated environments, attack taxonomies, and multi-layered failure analysis across reasoning, behavior,...

  5. Signal-Driven Observation for Long-Horizon Web Agents

    cs.CL 2026-06 unverdicted novelty 6.0

    Signal-Driven Observation decouples observation from action frequency in long-horizon web agents by invoking selective task-relevant DOM reads only on signals such as URL changes or action failures.

  6. Mobile GUI Agents under Real-world Threats: Are We There Yet?

    cs.CR 2025-07 conditional novelty 6.0

    Introduces an app-content instrumentation framework and benchmark showing that examined GUI agents suffer 42.0% and 36.1% average misleading rates from third-party content in dynamic and static tests respectively.

  7. Progent: Securing AI Agents with Privilege Control

    cs.CR 2025-04 unverdicted novelty 6.0

    Progent introduces a privilege-control framework for AI agents that uses LLM-generated symbolic rules over tools, SMT-solver-enforced monotonic updates, and deterministic checks to reduce attack success rates on Agent...

  8. WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections

    cs.CR 2026-05 unverdicted novelty 5.0

    WARD is a guard model trained on 177K web samples and adversarially hardened via attacker-guard co-evolution to achieve high recall on prompt injections with low false positives and no added latency.

  9. LaSM: Layer-wise Scaling Mechanism for Defending Pop-up Attack on GUI Agents

    cs.CR 2025-07 conditional novelty 5.0

    LaSM is a layer-wise scaling mechanism that amplifies attention and MLP modules in critical layers to defend GUI agents against pop-up attacks by correcting attention misalignment.

  10. Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges

    cs.AI 2025-10 unverdicted novelty 4.0

    A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.

  11. LLM Agents Are the Antidote to Walled Gardens

    cs.LG 2025-06 unverdicted novelty 4.0

    LLM agents enable universal interoperability by serving as automatic translators and adapters between proprietary digital services.