Escaping Alignment: A Physical Trap Model of Best-of-N Jailbreaking

arXiv:2609.32116 · cs.AI, cond-mat.stat-mech · Submitted 2026-09-26 · Read on arXiv

cs.AI, cond-mat.stat-mech

Submitted: 2026-09-26

Updated: 2026-09-26

Terminology

• Alignment — 15× in this paper · explained in 1 episode
• Robustness — 5× in this paper · explained in 5 episodes
• Embeddings — 3× in this paper · explained in 2 episodes
• Adversarial Attacks — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Calibration — 2× in this paper · explained in 7 episodes
• Scaling Laws — 2× in this paper · explained in 4 episodes
• AUC — 1× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Adversarial Robustness — 1× in this paper · explained in 3 episodes
• Attack Success Rate (ASR) — 1× in this paper · explained in 2 episodes
• Best-of-N Sampling — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Linear probe — 1× in this paper · explained in 2 episodes
• Maximum Likelihood Estimation — 1× in this paper
• Representation Engineering — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Jailbreak Scaling Laws for Large Language Models: Polynomial-Exponential Crossover
• Statistical Estimation of Adversarial Risk in Large Language Models under Best-of-N Sampling
• Qwen2.5 Technical Report
• The Llama 3 Herd of Models
• Gemma 2: Improving Open Language Models at a Practical Size
• Universal and Transferable Adversarial Attacks on Aligned Language Models
• Learning Curve Theory
• Efficient Prediction of Pass@k Scaling in Large Language Models
• Representation Engineering: A Top-Down Approach to AI Transparency
• Granite Guardian

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection