CounterPersona: Append-Only Defense Against Unauthorized Persona Skill Distillation

arXiv:2609.15097 · cs.CR · Submitted 2026-09-14 · Read on arXiv

cs.CR

Submitted: 2026-09-14

Updated: 2026-09-14

Comments: 30 pages, 7 figures

Code: https://github.com/agenmod/immortal-skill

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

Terminology

• Distillation — 85× in this paper · explained in 2 episodes
• Consistency — 17× in this paper · explained in 3 episodes
• Core — 17× in this paper · explained in 2 episodes
• Robustness — 13× in this paper · explained in 5 episodes
• Ablation — 8× in this paper · explained in 1 episode
• Trace — 7× in this paper · explained in 2 episodes
• Agent Skills — 6× in this paper · explained in 1 episode
• Calibration — 3× in this paper · explained in 7 episodes
• Empirical Methods in Natural Language Processing — 3× in this paper
• LLM-as-a-Judge — 3× in this paper · explained in 3 episodes
• Communication Styles Inventory — 2× in this paper
• Embeddings — 2× in this paper · explained in 2 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Machine Unlearning — 2× in this paper · explained in 2 episodes
• Multi-Session Chat — 2× in this paper
• Provenance — 2× in this paper · explained in 4 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Accountability — 1× in this paper · explained in 2 episodes
• Agentic System — 1× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Big Five Aspect Scales — 1× in this paper
• CVF International Conference on Computer Vision — 1× in this paper
• Chain-of-Thought (CoT) — 1× in this paper · explained in 4 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Knowledge Distillation — 1× in this paper · explained in 11 episodes
• Perplexity — 1× in this paper · explained in 3 episodes
• Personalization — 1× in this paper · explained in 2 episodes
• Procedural Knowledge — 1× in this paper · explained in 2 episodes

Sources

• Distilling the Knowledge in a Neural Network
• Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality
• SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision
• TOFU: A Task of Fictitious Unlearning for LLMs
• Anything2Skill: Compiling External Knowledge into Reusable Skills for Agents
• Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models
• SkillX: Automatically Constructing Skill Knowledge Bases for Agents
• Voyager: An Open-Ended Embodied Agent with Large Language Models
• SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
• Search2Skill: Skill Distillation Beyond Knowledge Boundaries Via Rubric-Based Reinforcement Learning
• COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation

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