InfoResearchPreprintLLM-specific
HalluProbe: Exploiting VLM Hallucinations for Backdoor Detection
- Published
- Record updated
Summary
Researchers show that backdoored Vision-Language Models hallucinate their backdoor target tokens more often across diverse inputs, while clean models produce random hallucinations without a stable target bias. They propose HalluProbe, which enhances hallucinations during output decoding and measures the distributional consistency of hallucinated tokens to flag backdoored models. Evaluated against six VLM backdoor attacks on three models, HalluProbe detects backdoored VLMs with over 90% accuracy, outperforming existing detection methods.
Topics
Related items
- InfoTrust-gated robust median: Root-free defense against backdoor attacks in Non-IID federated learningSimilar attack · Elsevier Security Journals
- HighCVE-2026-67455: NVIDIA Model Optimizer for Linux and Windows deserialization of untrusted dataSimilar attack · NVD/CVE Database
- MediumThe risks of device code authentication for AI coding agentsSimilar attack · Microsoft Security Blog
- MediumGrok Bots Attempt to Access Corporate Data Without User ApprovalSimilar attack · Dark Reading
- HighSiemens Mendix Studio ProSimilar attack · CISA Cybersecurity Advisories