SMInject: Specious Malignant Injection Attacks With Semantically-Enhanced Tokens in Cross-Modal Retrieval

Summary

SMInject is a new injection attack framework against pre-trained multimodal models used in cross-modal retrieval. It generates deceptive injections that combine concepts through causal correlation across modalities, and aligns them in the encoded embedding space to boost effectiveness. On representative multimodal models, it reportedly achieves over 14% higher attack success rate and 6% higher Hit@5 than state-of-the-art methods while preserving overall model utility.

Topics

• Multimodal models

Related items

• HighCVE-2026-125271 - AWS API MCP Server Security Policy Bypass via Incorrect Operation Name NormalizationSimilar attack · AWS Security Bulletins
• HighGHSA-ghwv-vrp2-2975: Cocos AI Intra-handshake attested TLS implementation is vulnerable to TOCTOU AttacksSimilar attack · GitHub Advisory Database
• MediumGHSA-5m6c-38r8-5w76: Dagu MCP DAG specification read bypasses path containment and workspace isolationSimilar attack · GitHub Advisory Database
• HighCVE-2026-123818: LMDeploy is a toolkit for compressing, deploying, and serving large language models. From 0.12.3 until 0.15.0…Similar attack · NVD/CVE Database
• HighGHSA-vvr2-h2jp-838m: Code Graph RAG: MCP paginated read_file path traversal / arbitrary file readSimilar attack · GitHub Advisory Database