Beyond Vector Hiding: Breaking and Mitigating Shared-Direction Weight Obfuscation in TEE-Offloaded Large Language Models

arXiv:2608.26651 · cs.CR · Submitted 2026-08-27 · Read on arXiv

cs.CR

Submitted: 2026-08-27

Updated: 2026-08-27

Terminology

Accuracy — 35× in this paper · explained in 1 episode
Fine-Tuning — 8× in this paper · explained in 5 episodes
Trusted Execution Environment — 6× in this paper
Transformer — 5× in this paper · explained in 2 episodes
Cosine Similarity — 4× in this paper · explained in 3 episodes
IEEE Symposium on Security and Privacy — 4× in this paper
Alignment — 3× in this paper · explained in 1 episode
International Conference on Machine Learning — 3× in this paper
Benchmark — 2× in this paper · explained in 2 episodes
Consistency — 2× in this paper · explained in 3 episodes
Information Leakage — 2× in this paper · explained in 2 episodes
Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
Learning with Errors — 2× in this paper
Quantization — 2× in this paper · explained in 12 episodes
Ablation — 1× in this paper · explained in 1 episode
Adaptation — 1× in this paper · explained in 1 episode
Edge Devices — 1× in this paper · explained in 2 episodes
Embeddings — 1× in this paper · explained in 2 episodes
Fingerprinting — 1× in this paper · explained in 2 episodes
International Conference on Learning Representations — 1× in this paper
Transfer Learning — 1× in this paper · explained in 10 episodes
Transformer Models — 1× in this paper · explained in 2 episodes

Sources

Related papers