Pedro H. Barcha Correia, Matheus Azevedo de Sá, Paulo H. Gomes de Senna, Giovanni Mandel Martignago, Victor Takashi Hayashi, Charles Christian Miers, Marcos A. Simplicio · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28810 · open-access PDF
近年、生成型人工知能の広範な採用は、即時注入とジャイルブレイク攻撃の同時増加をもたらしました。悪意のある指示を組み込むことで、これらのエクスペリエイトは言語モデルを操作して、意図された行動と運用の限界を回避します。伝統的なチャットボットでは、このような攻撃は、会話を通じてステータスメモリが保存されていないため、1つのセッションに限定されています。
Machine translation (Meta M2M100); the English original follows.
The widespread adoption of generative artificial intelligence in recent years has brought a parallel rise in prompt injection and jailbreak attacks. By embedding malicious instructions, these exploits manipulate language models to bypass intended behavior and operational boundaries. In traditional chatbots, such attacks are confined to a single session because state memory is not preserved across conversations. However, persistent memory features in modern conversational interfaces enable cross-session attack propagation, establishing a threat vector known as memory injection. This work explor
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28810, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange