Secure Speculative Decoding for Large Language Models

arXiv:2610.08678 · cs.CR, cs.AI, cs.LG · Submitted 2026-10-06 · Read on arXiv

cs.CR, cs.AI, cs.LG

Submitted: 2026-10-06

Updated: 2026-10-13

Code: https://github.com/YichiCS/Secure-Speculative-Decoding

Terminology

• Speculative Decoding — 1× in this paper · explained in 2 episodes

Sources

• Accelerating Large Language Model Decoding with Speculative Sampling
• AdaSD: Adaptive Speculative Decoding for Efficient Language Model Inference
• Universal and Transferable Adversarial Attacks on Aligned Language Models
• PIArena: A Platform for Prompt Injection Evaluation
• Evaluating Large Language Models Trained on Code
• Training Verifiers to Solve Math Word Problems

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