# Scaling Patterns in Adversarial Alignment: Evidence from Multi-LLM Jailbreak Experiments

arXiv: https://arxiv.org/abs/2511.13788 · HTML: https://mlsanity.com/paper/2511.13788/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Jailbreaking, one of 12 directions in LLM safety and security.
- Builds on 17 of its 30 references that are in the map.
- First posted on arXiv 16 Nov 2025.

## Placed in

- LLM safety and security / [Jailbreaking](https://mlsanity.com/safety/jailbreaking/)

## Builds on (most cited first, 17 of 17)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs](https://mlsanity.com/paper/2401.06373/) (2024)
- [JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models](https://mlsanity.com/paper/2404.01318/) (2024)
- [An Overview of Catastrophic AI Risks](https://mlsanity.com/paper/2306.12001/) (2023)
- [The Capacity for Moral Self-Correction in Large Language Models](https://mlsanity.com/paper/2302.07459/) (2023)
- [Agentic Misalignment: How LLMs Could Be Insider Threats](https://mlsanity.com/paper/2510.05179/) (2025)
- [The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation](https://mlsanity.com/paper/2312.09085/) (2023)
- [Multi-Turn Jailbreaks Are Simpler Than They Seem](https://mlsanity.com/paper/2508.07646/) (2025)
- [Logic Jailbreak: Efficiently Unlocking LLM Safety Restrictions Through Formal Logical Expression](https://mlsanity.com/paper/2505.13527/) (2025)
- [JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring](https://mlsanity.com/paper/2508.20848/) (2025)
- [Large Reasoning Models Are Autonomous Jailbreak Agents](https://mlsanity.com/paper/2508.04039/) (2025)
- [xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking](https://mlsanity.com/paper/2501.16727/) (2025)
- [Confusion is the Final Barrier: Rethinking Jailbreak Evaluation and Investigating the Real Misuse Threat of LLMs](https://mlsanity.com/paper/2508.16347/) (2025)

## Built on by (most cited first, 2 of 2)

- [Replicating TEMPEST at Scale: Multi-Turn Adversarial Attacks Against Trillion-Parameter Frontier Models](https://mlsanity.com/paper/2512.07059/) (2025)
- [AUDITPLAN: Commit, Then Answer for Auditable Safety Alignment](https://mlsanity.com/paper/2609.19325/) (2026)

## Abstract (arXiv)

Large language models (LLMs) increasingly operate in multi-agent and safety-critical settings, raising open questions about how their vulnerabilities scale when models interact adversarially. This study examines whether larger models can systematically jailbreak smaller ones - eliciting harmful or restricted behavior despite alignment safeguards. Using standardized adversarial tasks from JailbreakBench, we simulate over 6,000 multi-turn attacker-target exchanges across major LLM families and scales (0.6B-120B parameters), measuring both harm score and refusal behavior as indicators of adversarial potency and alignment integrity. Each interaction is evaluated through aggregated harm and refusal scores assigned by three independent LLM judges, providing a consistent, model-based measure of adversarial outcomes. Aggregating results across prompts, we find a strong and statistically significant correlation between mean harm and the logarithm of the attacker-to-target size ratio (Pearson r = 0.51, p < 0.001; Spearman rho = 0.52, p < 0.001), indicating that relative model size correlates with the likelihood and severity of harmful completions. Mean harm score variance is higher across attackers (0.18) than across targets (0.10), suggesting that attacker-side behavioral diversity contributes more to adversarial outcomes than target susceptibility. Attacker refusal frequency is strongly and negatively correlated with harm (rho = -0.93, p < 0.001), showing that attacker-side alignment mitigates harmful responses. These findings reveal that size asymmetry influences robustness and provide exploratory evidence for adversarial scaling patterns, motivating more controlled investigations into inter-model alignment and safety.