Ranked but Not Stopped: Detecting Prompt-Injection Hijacks from Typed Decision Models' Output Probabilities
cs.CL, cs.CR
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- One Word Opens the Gate: The Option-Channel Attack on Typed Decision Models as Agent Guardrails
- Confidently Wrong: Severity-Aware Calibration of Prompt-Injection Detectors under Attack Shift
- Probability Contracts: Accuracy, Coherence, and Decisions Across LLM Interfaces
- SecJev: Bringing Security Expertise to System One Decision Models
- How Not to Detect Prompt Injections with an LLM
- Detecting Adversarial Samples from Artifacts
- Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
- Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures
- Are You Reading the Right Thing? Rethinking Internal Signals for Prompt-Injection Detection
- JevAdvBench: A Benchmark and Black-Box Attacks for Reinforcement Learning for Calibrated Decisions Models
- Same Answer, Different Confidence: Protocol Sensitivity in LLM Confidence Calibration
- From Detection to Decision: Calibration and Deferral for Prompt-Injection Detection
- Building Efficient Universal Classifiers with Natural Language Inference
- JEV-as-a-Judge: Accept When Confident, Escalate When Unsure
- Counterfactual Evaluation for Blind Attack Detection in LLM-based Evaluation Systems
- Evaluating System One Models for Agent Security Decisions: Reliability, Calibration, and Selective Automation
- The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections
- Are Large Language Models More Honest in Their Probabilistic or Verbalized Confidence?
- Jev thinks "I don't know'', but doesn't say it: Introducing Sys1Cal-v1 Dataset for Probability Calibration
- Typed Decision Models: An Early Evidence Audit and Evaluation Checklist
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data