ライフサイクルを考慮した動的解析による安全なMLモデル実行の実現
Lifecycle-Aware Dynamic Analysis for Secure ML Model Execution
MLモデルの実行をライフサイクルフェーズに分け、各フェーズでのホストシステムとの相互作用を監視する動的解析手法を提案し、既存の静的スキャンでは検出できない攻撃を高い精度で検出した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Gabriele Digregorio, Marco Di Gennaro, Francesco Pastore, Stefano Zanero, Stefano Longari, Michele Carminati
分類: cs.CR, cs.LG
原文アブストラクト
The growing reliance on pre-trained Machine Learning (ML) models has introduced new attack surfaces. Recent vulnerabilities demonstrate that malicious behavior can be embedded within model artifacts, often bypassing existing defenses. Current model-scanning solutions primarily rely on static, format-specific rules or known attack signatures, which limit their ability to generalize across frameworks and to detect novel exploitation paths. In contrast, we propose a solution that focuses on the effects an attack has on the host system executing the model and builds on foundational intuitions about ML model execution. In particular, we observe that ML models operate within well-defined lifecycle phases and that, within each phase, interactions with the host system are highly structured and predictable. We translate these intuitions into Moat, a dynamic lifecycle-aware approach for securing ML model execution, and instantiate this design in Re-Moat, our reference implementation. We evaluate Re-Moat across multiple ML frameworks using 77,974 real-world model artifacts from the Hugging Face Hub, 31 Proofs-of-Concept (PoCs) from CVEs, and 334 models from a state-of-the-art dataset, and compare it against state-of-the-art model-scanning solutions. Our results show that our approach detects all evaluated attack classes while maintaining a close-to-zero false-positive rate, validating our intuitions and motivating dynamic analysis for securing ML model execution.
