Not All Tokens Are Equal: Region-Aware Consistency Repair of Backdoors in MLLMs

arXiv:2608.24354 · cs.CR, cs.AI, cs.CL · Submitted 2026-08-25 · Read on arXiv

cs.CR, cs.AI, cs.CL

Submitted: 2026-08-25

Updated: 2026-08-25

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Pruning — 51× in this paper · explained in 4 episodes
• Fine-Tuning — 37× in this paper · explained in 5 episodes
• Quantization — 25× in this paper · explained in 12 episodes
• Accuracy — 21× in this paper · explained in 1 episode
• Consistency — 21× in this paper · explained in 3 episodes
• Aggregation — 16× in this paper · explained in 1 episode
• Benchmark — 7× in this paper · explained in 2 episodes
• Regularization — 4× in this paper · explained in 3 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Domain Shift — 3× in this paper · explained in 4 episodes
• Instruction Tuning — 3× in this paper · explained in 2 episodes
• Adversarial Training — 2× in this paper · explained in 1 episode
• Trace — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• alpha — 2× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Adversarial Attacks — 1× in this paper · explained in 1 episode
• Attack Success Rate (ASR) — 1× in this paper · explained in 2 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Few-Shot Learning — 1× in this paper · explained in 4 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
• Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
• Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
• Qwen2.5-VL Technical Report
• Test-Time Attention Purification for Backdoored Large Vision Language Models
• Microsoft COCO Captions: Data Collection and Evaluation Server
• BackdoorVLM: A Benchmark for Backdoor Attacks and Defenses on Vision-Language Models

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