# Surviving the Unseen: Predictive Defense for Novel Multi-Turn Multimodal Attacks

arXiv: https://arxiv.org/abs/2605.18988 · HTML: https://mlsanity.com/paper/2605.18988/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 25 references that are in the map.
- First posted on arXiv 18 May 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)
- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 16 of 16)

- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models](https://mlsanity.com/paper/2310.04451/) (2023)
- [Likelihood Ratios for Out-of-Distribution Detection](https://mlsanity.com/paper/1906.02845/) (2019)
- [Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack](https://mlsanity.com/paper/2404.01833/) (2024)
- [DeepSurv: Personalized Treatment Recommender System Using A Cox Proportional Hazards Deep Neural Network](https://mlsanity.com/paper/1606.00931/) (2016)
- [Foot-In-The-Door: A Multi-turn Jailbreak for LLMs](https://mlsanity.com/paper/2502.19820/) (2025)
- [Mahalanobis++: Improving OOD Detection via Feature Normalization](https://mlsanity.com/paper/2505.18032/) (2025)
- [Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges](https://mlsanity.com/paper/2510.23883/) (2025)
- [Multi-lingual Multi-turn Automated Red Teaming for LLMs](https://mlsanity.com/paper/2504.03174/) (2025)
- [Time-To-Inconsistency: A Survival Analysis of Large Language Model Robustness to Adversarial Attacks](https://mlsanity.com/paper/2510.02712/) (2025)
- [Detecting LLM-Assisted Academic Dishonesty using Keystroke Dynamics](https://mlsanity.com/paper/2511.12468/) (2025)
- [Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models](https://mlsanity.com/paper/2602.01025/) (2026)
- [PolyJailbreak: Cross-Modal Jailbreaking Attacks on Black-Box Multimodal LLMs](https://mlsanity.com/paper/2510.17277/) (2025)
- [Multi-turn Jailbreaking Attack in Multi-Modal Large Language Models](https://mlsanity.com/paper/2601.05339/) (2026)

## Abstract (arXiv)

The expansion of Multimodal Large Language Models (MLLMs) and their integration into autonomous agentic workflows has introduced a non-stationary attack surface. Empirical observations indicate that adversaries employ progressive, cross-modal perturbations that evade turn-specific guardrails by distributing malicious intent across longitudinal conversational trajectories. Static defense mechanisms, constrained by the Markov property, evaluate inputs in isolation and fail to detect cumulative structural poisoning. To handle this limitation, this paper formulates safety verification as a dynamic survival prediction and trajectory dynamics problem. The Triple-tier Anomaly Defense (TRIAD) framework is proposed as a predictive model that maps multimodal and multi-turn conversational flow as a continuous trajectory. The framework integrates structural anomaly detection to monitor covariance shifts, a Ledoit-Wolf regularized Mahalanobis distance to monitor covariance shifts in high-dimensional spaces, and topological trajectory acceleration to differentiate benign creative exploration from continuous malicious drift. These kinematic and geometric features are integrated into a time-varying Cox Proportional Hazards model via a Bayesian Hidden Markov Model (HMM) feedback loop. Theoretical analysis demonstrates that the TRIAD framework provides a mathematically bounded expected time-to-failure under adversarial perturbations, ensuring that malicious acceleration diverges positively. This framework provides a computationally efficient, interpretable, and predictive safeguard for real-time agentic AI systems, establishing a rigorous foundation for continuous safety alignment without relying on empirical retraining.