الملخص
تمت ترجمة أجزاء من هذه الصفحة آلياً وقد تحتوي على أخطاء.
Pre-trained models (PTMs) are widely distributed as serialized binaries, but their reuse often exposes software supply chains to deserialization attacks. Despite the emergence of safer serialization formats, the unsafe Pickle format remains prevalent: our analysis of over 10,000 popular Hugging Face repositories reveals that 9.3% rely on Pickle. While many defense mechanisms have been proposed, state-of-the-art model scanners suffer from a coverage-precision gap, missing security-sensitive behaviors and generating excessive false alerts. In this paper, we introduce DITTO, the first stack-based, context-aware scanner for Pickle-based PTMs. DITTO faithfully tracks Pickle virtual machine state transitions and performs context-aware semantic analysis to infer model intentions. We also present PickleBench, a benchmark of 959 benign and 92 malicious real-world models, including extension registry attacks previously missed by existing tools. Across multiple evaluations, DITTO achieves 100% scanning coverage, a 0% false-negative rate, and a 0.7% false-positive rate, yielding an F1 score of 0.966, significantly outperforming state-of-the-art scanners. By minimizing false alerts while preserving detection accuracy, DITTO generates actionable security reports with contextual evidence, enabling safe PTM reuse and strengthening software supply chain integrity.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Qin, Q., Li, W., Baudry, B., De Carli, L., Li, H., & Merlo, E. (2026). DITTO: ماسح نماذج مدرَّبة مسبقًا قائم على Pickle ومدرك للسياق لتدقيقات أمنية فعّالة. https://omanscience.com/ar/articles/ditto-a-context-aware-pickle-based-pre-trained-model-scanner-for-effective-security-audits
MLA 9
Qin, Qiaolin, et al. "DITTO: ماسح نماذج مدرَّبة مسبقًا قائم على Pickle ومدرك للسياق لتدقيقات أمنية فعّالة." https://omanscience.com/ar/articles/ditto-a-context-aware-pickle-based-pre-trained-model-scanner-for-effective-security-audits.
شيكاغو (المؤلف–التاريخ)
Qin, Qiaolin, Wanpeng Li, Benoit Baudry, Lorenzo De Carli, Heng Li, and Ettore Merlo. 2026. "DITTO: ماسح نماذج مدرَّبة مسبقًا قائم على Pickle ومدرك للسياق لتدقيقات أمنية فعّالة." https://omanscience.com/ar/articles/ditto-a-context-aware-pickle-based-pre-trained-model-scanner-for-effective-security-audits.
هارفارد
Qin, Q., Li, W., Baudry, B., De Carli, L., Li, H. and Merlo, E. (2026) 'DITTO: ماسح نماذج مدرَّبة مسبقًا قائم على Pickle ومدرك للسياق لتدقيقات أمنية فعّالة', Available at: https://omanscience.com/ar/articles/ditto-a-context-aware-pickle-based-pre-trained-model-scanner-for-effective-security-audits.
فانكوفر
Qin Q, Li W, Baudry B, De Carli L, Li H, Merlo E. DITTO: ماسح نماذج مدرَّبة مسبقًا قائم على Pickle ومدرك للسياق لتدقيقات أمنية فعّالة. https://omanscience.com/ar/articles/ditto-a-context-aware-pickle-based-pre-trained-model-scanner-for-effective-security-audits
IEEE
Q. Qin, W. Li, B. Baudry, L. De Carli, H. Li, and E. Merlo, "DITTO: ماسح نماذج مدرَّبة مسبقًا قائم على Pickle ومدرك للسياق لتدقيقات أمنية فعّالة," https://omanscience.com/ar/articles/ditto-a-context-aware-pickle-based-pre-trained-model-scanner-for-effective-security-audits.