JevBreak: Your Model, Their Decision
cs.CR, cs.AI
Submitted: 2026-11-02
Updated: 2026-11-02
Code: https://github.com/atlanai/decision-bench
Terminology
Sources
- One Word Opens the Gate: The Option-Channel Attack on Typed Decision Models as Agent Guardrails
- JevAdvBench: A Benchmark and Black-Box Attacks for Reinforcement Learning for Calibrated Decisions Models
- DecisionRobust: Benchmarking Robustness for JEV Style Decision Models Across Text and Vision
- Same Attack, Different Judge: A First Controlled Adversarial Comparison of Jev, LLM Judges, and Purpose-Built Safety Classifiers
- JEV-as-a-Judge: Accept When Confident, Escalate When Unsure
- Type-Safe Is Not Error-Free: Typed Decision Models Follow the Option Name, Not the Definition Bound to It
- Decision Hijacking: Prompt Injection Attacks on Jev's Typed Probabilistic Decisions
- JevOut: Natural Context Can Flip Decision Models
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data