Metraipolis › archive › dc_abfa352a08da

The Web Doesn't Sit Still: Adversarial Self-Evolving Attacks on Search Agents — arXiv:2611.03754

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.03754
License (as archived): CC0-1.0
Archived: 2026-11-04T18:35:39.869Z
SHA-256 of the archived text: ce459214858448c71e180fb94e3813e8391382d10c218c4a5c7a620baf1203f2
Stable URL of this page: https://metraipolis.com/documento/dc_abfa352a08da

How to cite

The Web Doesn't Sit Still: Adversarial Self-Evolving Attacks on Search Agents — arXiv:2611.03754 — arXiv (en), https://arxiv.org/abs/2611.03754 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_abfa352a08da (Metraipolis archive dc_abfa352a08da, sha256 ce459214858448c71e180fb94e3813e8391382d10c218c4a5c7a620baf1203f2)

BibTeX

@misc{dcabfa352a08da,
  title = {The Web Doesn't Sit Still: Adversarial Self-Evolving Attacks on Search Agents — arXiv:2611.03754},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03754},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_abfa352a08da; sha256 ce459214858448c71e180fb94e3813e8391382d10c218c4a5c7a620baf1203f2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03754. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Models (LLMs) have shown promise for empowering search agents to tackle complex information-seeking tasks. However, since acquiring external information necessitates web search, these agents are highly susceptible to various adversarial attacks (e.g., malicious information injection or stealthy context manipulation). Existing attack strategies inevitably rely on static and human-crafted templates, failing to emulate the dynamic and complex nature of real-world threats. In this paper, we propose an adversarial self-evolution framework that integrates bi-level optimization between the attacker's strategy evolution and the defender's adaptive mitigation, to expose the vulnerabilities of search agents. Specifically, we introduce the Contrastive Rollout Evolutionary Optimization (CREO) method to drive the directional evolution of the attack strategy population via contrastive evolutionary signals. To provide a stable environment for this continuous evolution, we further construct a controlled sandbox and design fine-grained metrics to quantify internal vulnerabilities. Extensive experiments across various multi-hop QA benchmarks and frontier LLMs demonstrate that the proposed framework yields attack efficacy superior to static baselines, underscoring the urgent need to develop more robust defense frameworks.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.03754 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-04T18:32:37.383Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).