Metraipolis › archive › dc_ea4f609cddeb

Temporal Context Awareness: A Defense Framework Against Multi-turn Manipulation Attacks on Large Language Models — arXiv:2503.15560

Source: arXiv (en)
Original: https://arxiv.org/abs/2503.15560
License (as archived): CC0-1.0
Archived: 2026-10-31T11:13:20.672Z
SHA-256 of the archived text: 0ad107faf353ac87d7b9a3724af269f6e2e669662af73f8f18713f8b579f2fb2
Stable URL of this page: https://metraipolis.com/documento/dc_ea4f609cddeb

How to cite

Temporal Context Awareness: A Defense Framework Against Multi-turn Manipulation Attacks on Large Language Models — arXiv:2503.15560 — arXiv (en), https://arxiv.org/abs/2503.15560 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ea4f609cddeb (Metraipolis archive dc_ea4f609cddeb, sha256 0ad107faf353ac87d7b9a3724af269f6e2e669662af73f8f18713f8b579f2fb2)

BibTeX

@misc{dcea4f609cddeb,
  title = {Temporal Context Awareness: A Defense Framework Against Multi-turn Manipulation Attacks on Large Language Models — arXiv:2503.15560},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2503.15560},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ea4f609cddeb; sha256 0ad107faf353ac87d7b9a3724af269f6e2e669662af73f8f18713f8b579f2fb2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2503.15560. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Models (LLMs) are increasingly vulnerable to sophisticated multi-turn manipulation attacks, where adversaries strategically build context through seemingly benign conversational turns to circumvent safety measures and elicit harmful or unauthorized responses. These attacks exploit the temporal nature of dialogue to evade single-turn detection methods, representing a critical security vulnerability with significant implications for real-world deployments. This paper introduces the Temporal Context Awareness (TCA) framework, a novel defense mechanism designed to address this challenge by continuously analyzing semantic drift, cross-turn intention consistency and evolving conversational patterns. The TCA framework integrates dynamic context embedding analysis, cross-turn consistency verification, and progressive risk scoring to detect and mitigate manipulation attempts effectively. Preliminary evaluations on simulated adversarial scenarios demonstrate the framework's potential to identify subtle manipulation patterns often missed by traditional detection techniques, offering a much-needed layer of security for conversational AI systems. In addition to outlining the design of TCA , we analyze diverse attack vectors and their progression across multi-turn conversation, providing valuable insights into adversarial tactics and their impact on LLM vulnerabilities. Our findings underscore the pressing need for robust, context-aware defenses in conversational AI systems and highlight TCA framework as a promising direction for securing LLMs while preserving their utility in legitimate applications. We make our implementation available to support further research in this emerging area of AI security.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.AI).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2503.15560 — 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 2026-10-31T11:02:13.447Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).