Post-Hoc Trajectory-Risk Certification for Modular LLM-Based Security Agents

arXiv:2608.05199 · cs.CR, cs.AI · Submitted 2026-08-04 · Read on arXiv

Zhenpeng Li

cs.CR, cs.AI

Submitted: 2026-08-04

Comments: 18 pages, 11 tables; preprint

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

Terminology

• Calibration — 26× in this paper · explained in 7 episodes
• Conformal Prediction — 17× in this paper · explained in 5 episodes
• Accuracy — 14× in this paper · explained in 1 episode
• Exchangeability — 14× in this paper · explained in 2 episodes
• Trajectory Coverage — 14× in this paper
• Distribution Shift — 6× in this paper · explained in 6 episodes
• Sample Complexity — 3× in this paper · explained in 15 episodes
• Verification — 3× in this paper · explained in 2 episodes
• Concept Drift — 2× in this paper · explained in 4 episodes
• Degeneracy — 2× in this paper · explained in 3 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Provenance — 2× in this paper · explained in 4 episodes
• Trajectory Miscoverage Rate — 2× in this paper
• Abstention — 1× in this paper · explained in 1 episode
• Abstraction — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Adversarial Robustness — 1× in this paper · explained in 3 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• International Conference on Learning Representations — 1× in this paper
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Uncertainty Quantification — 1× in this paper · explained in 8 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• On Calibration of Modern Neural Networks
• PASC: Pipeline-Aware Conformal Prediction with Joint Coverage Guarantees for Multi-Stage NLP and LLM Pipelines
• Conformal Selective Acting: Anytime-Valid Risk Control for RLVR-Trained LLMs
• The Llama 3 Herd of Models
• Mistral 7B

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