跳到正文
Jones Ray

ScholarPulse 日报 2026-08-06

2026-08-06 学术简报:2 篇。PIMiner通过构建可迁移策略库,实现提示注入红队测试的高效泛化,显著提升对多种LLM的攻击成功率。

今日速览

序号标题来源日期主题推荐等级
1Agent Against Agent: An Agentic System for Automatic Prompt Injection Red TeamingarXiv2026-08-05AI-Agent高
2CoPlan: A Trustworthy Co-Intelligence Interface for Care Planning through Role-Based Contestable Argument GraphsarXiv2026-08-05AI-Agent高

重点论文与技术动态

1. Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming

一句话结论

PIMiner通过构建可迁移策略库,实现提示注入红队测试的高效泛化,显著提升对多种LLM的攻击成功率。

核心内容

方法与数据

价值判断

摘要 Prompt injection poses significant security risks to LLM agents. Efficient and effective red-teaming is therefore critical, both for evaluating these risks and for collecting training data to improve defenses. Existing state-of-the-art prompt injection red-teaming methods primarily rely on reinforcement learning (RL), producing attacker models that often generalize poorly to new target LLMs. In this work, we develop PIMiner, an agentic system for prompt injection red-teaming. During training, PIMiner is trained on a sequence of (dataset, target model) pairs and builds a strategy library from scratch. At test time, the learned strategy library can be directly transferred to a previously unseen target LLM without additional training. PIMiner requires only a small number of queries to a target agent (e.g., 10) per test sample. Experimental results demonstrate that PIMiner achieves strong performance. On IPIArena, it attains a 76.2% ASR against Gemini-2.5-Pro, 61.9% ASR against GPT-5.1, and 42.9% ASR against Claude-Sonnet-4.5. On AgentDojo, it achieves an 86.7% ASR against Gemini-2.5-Pro, 53.3% ASR against GPT-5.1, and 40.0% ASR against Claude-Sonnet-4.5.

2. CoPlan: A Trustworthy Co-Intelligence Interface for Care Planning through Role-Based Contestable Argument Graphs

一句话结论

CoPlan通过角色化可争议论点图实现可信的协作智能护理规划界面。

核心内容

方法与数据

价值判断

摘要 AI-supported care planning can help clinicians, patients, caregivers, and care teams coordinate complex decisions across clinical, functional, psychosocial, and environmental needs. However, many AI systems present recommendations as fixed outputs, limiting stakeholders' ability to inspect, challenge, and revise plans when they conflict with clinical judgment, patient values, or real-world feasibility. We present CoPlan - a Co-Intelligent and Contestable Interface for Human-AI Care Planning. CoPlan uses a multi-agent workflow in which specialized AI agents generate candidate interventions and supporting or challenging arguments, while human care planners can accept, reject, modify, or add arguments before final plan generation. Through this design, CoPlan combines co-intelligence, in which humans and AI agents contribute complementary expertise, with contestability, where recommendations remain open to inspection, revision, and justification. We demonstrate CoPlan in an aging-in-place care planning scenario. The system supports adaptive care team recruitment, role-based argument review, final care plan generation, and practical follow-up through scheduling agents. This work contributes a contestable care planning interface and a design framing for trustworthy human-AI care planning that preserves human agency and clinical accountability.