SAGE: Efficient Protected Vision-Language Inference on Smart Glasses
cs.CR, cs.AI, cs.CE
Submitted: 2026-10-08
Updated: 2026-10-08
Sources
- Token Merging: Your ViT But Faster
- Censoring Representations with an Adversary
- Who Can See Through You? Adversarial Shielding Against VLM-Based Attribute Inference Attacks
- Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- LoRA: Low-Rank Adaptation of Large Language Models
- Defending Wearable VLMs Against Private Attribute Inference
- TOFU: A Task of Fictitious Unlearning for LLMs
- Switch-KD: Visual-Switch Knowledge Distillation for Vision-Language Models
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
- MiniCPM-V: A GPT-4V Level MLLM on Your Phone
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