IPI-exposure-signal

IPI露出シグナル これは、私たちの論文「Your Agentic LLMs Secretly Encode Latent Signals of Indirect Prompt-Injection Exposure」のコードリポジトリです。 ArXiv版と論文リンク: https://arxiv.org/abs/2608.02657 このリポジトリは、潜在的なIPI露出シグナルのプロービングパイプライン（AgentDojoトレース収集、IPIリスクラベリング、隠れ状態のフィーチャー化、IPI露出プローブのトレーニング/評価）を実装しています。 引用...

Structural Inference in Undocumented Mobile Databases: A Reproducible Benchmark for Evaluating Agentic Reasoning in Digital Forensics

Agentic large language models are increasingly used in digital forensic analysis, yet their ability to infer relational structure inside undocumented mobile application databases remains poorly understood. In forensic contexts, structurally incorrect inferences can yield results that appear...

On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models

Large Language Models LLMs have undergone a shift from stateless conversational interfaces to autonomous agents capable of multi-step planning, tool invocation, code execution, and maintaining persistent memory. When these agents operate with real-world privileges---calling APIs, modifying files,...