Practical and Flexible Backdoor Attack Against Deep Learning Models via Shell Code Injection

Summary

Researchers propose shell code injection (SCI), a non-poisoning backdoor attack framework against deep learning models that needs no training. It uses a logic-driven backdoor shell with trigger consistency verification and short-circuit code packaging to force wrong predictions, and an LLM-assisted module generates attack target code adaptively. Experiments report almost 100% attack success rate (ASR) across various settings.

Topics

• Adversarial machine learning

Related items

• MediumCVE-2026-121936: easyVoice server-side request forgery through openaiBaseUrl in /api/v1/ttsSimilar attack · NVD/CVE Database
• MediumCVE-2026-118628: MLflow get-artifacts server-side request forgery information disclosureSimilar attack · NVD/CVE Database
• HighCVE-2026-118625: MLflow Tracking Server privilege escalation via get_endpointsSimilar attack · NVD/CVE Database
• InfoWhen trust becomes the payload: Inside the threats, etc quarterly reportSimilar attack · Elastic Security Labs
• MediumCritical Langflow flaws enable authentication bypass and RCESimilar attack · CSO Online