Understanding the Security Boundary of Obfuscation-based On-Device LLM Protection

arXiv:2609.10117 · cs.CR · Submitted 2026-09-09 · Read on arXiv

cs.CR

Submitted: 2026-09-09

Updated: 2026-09-17

Comments: 17 pages. Accepted to ACM CCS 2026 (Cycle B)

Code: https://github.com/gabber-gabber/Collapse

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

Terminology

• Accuracy — 26× in this paper · explained in 1 episode
• Fine-Tuning — 15× in this paper · explained in 5 episodes
• Transformer — 12× in this paper · explained in 2 episodes
• Alignment — 9× in this paper · explained in 1 episode
• Abstraction — 7× in this paper · explained in 1 episode
• TEE-Shielded LLM Partition — 4× in this paper
• Adaptation — 3× in this paper · explained in 1 episode
• Empirical Methods in Natural Language Processing — 3× in this paper
• Fidelity — 3× in this paper · explained in 2 episodes
• Fingerprinting — 3× in this paper · explained in 2 episodes
• IEEE Symposium on Security and Privacy — 3× in this paper
• Adversarial Attacks — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Generalizability — 2× in this paper · explained in 6 episodes
• In International Conference on Learning Representations — 2× in this paper
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Quantization — 2× in this paper · explained in 12 episodes
• Rich Execution Environment — 2× in this paper
• Conference on Computer Vision and Pattern Recognition — 1× in this paper
• Core — 1× in this paper · explained in 2 episodes
• Edge Deployment — 1× in this paper · explained in 2 episodes
• General Language Understanding Evaluation — 1× in this paper
• Generative AI — 1× in this paper · explained in 2 episodes
• In International Conference on Machine Learning — 1× in this paper
• Redundancy — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• SIGSAC Conference on Computer and Communications Security — 1× in this paper
• Sparsity — 1× in this paper · explained in 4 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transformer Models — 1× in this paper · explained in 2 episodes

Sources

• Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
• Gemini: A Family of Highly Capable Multimodal Models
• Apple Intelligence Foundation Language Models
• Qwen2.5 Technical Report
• LLaMA: Open and Efficient Foundation Language Models
• Confidential Computing on Heterogeneous CPU-GPU Systems: Survey and Future Directions

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