TokenScanner: Detecting Backdoors and Discovering Triggers in Text-to-Image LoRAs via Full Vocabulary Scanning

arXiv:2609.31878 · cs.CR · Submitted 2026-09-25 · Read on arXiv

cs.CR

Submitted: 2026-09-25

Updated: 2026-09-25

Terminology

• Diffusion Model — 20× in this paper · explained in 8 episodes
• Diffusion Models — 19× in this paper · explained in 6 episodes
• Adaptation — 12× in this paper · explained in 1 episode
• AUC — 9× in this paper · explained in 2 episodes
• LoRA Adaptation — 4× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Ablation study — 3× in this paper · explained in 1 episode
• Embeddings — 3× in this paper · explained in 2 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Verification — 3× in this paper · explained in 2 episodes
• Unified Framework — 2× in this paper · explained in 5 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Distribution Shift — 1× in this paper · explained in 6 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• Personalization — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transferability — 1× in this paper · explained in 4 episodes

Sources

• Semantic-level Backdoor Attack against Text-to-Image Diffusion Models
• Scaling Exposes the Trigger: Input-Level Backdoor Detection in Text-to-Image Diffusion Models via Cross-Attention Scaling

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs