Enforcing LLM Safety through DMD-based Classification of Prompt-Response Embedding Dynamics

• URL: http://arxiv.org/abs/2608.19579v1
• Date: Thu, 20 Aug 2026 02:50:44 GMT
• Title: Enforcing LLM Safety through DMD-based Classification of Prompt-Response Embedding Dynamics
• Abstract summary: Large Language Models (LLMs) are increasingly deployed in high-stakes applications, yet their tendency to generate toxic, harmful, or policy-violating content poses significant risks.<n>We extend a recently proposed dynamical systems framework designed for hallucination detection to LLM safety classification.
• Score: 5.114377181378075
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) are increasingly deployed in high-stakes applications, yet their tendency to generate toxic, harmful, or policy-violating content poses significant risks. Detecting these unsafe outputs efficiently in a black-box manner remains an open challenge. In this paper, we extend a recently proposed dynamical systems framework designed for hallucination detection to LLM safety classification. By projecting both prompts and responses into high-dimensional embedding spaces and fitting separate Koopman-based predictive models for safe and unsafe regimes, we classify new outputs using a new differential residual score that compares prediction errors of the safe and unsafe regimes. A key contribution is the incorporation of the prompt and response embedding dynamics, yielding fitted Koopman operators that capture crucial interaction patterns. We evaluate our black-box method across three safety benchmarks using three embedding models. Our results show that incorporating prompt embeddings yields consistent improvements, particularly for interaction-dependent violations when paired with causal decoders (e.g., in Llama-3), while response-only violations benefit more from dense semantic embedding representations. These findings opens the door for using dynamical systems to analyze AI systems rather than the dominant paradigm of using AI to model dynamical systems.

Related papers

• Disentangling Adversarial Prompts: A Semantic-Graph Defense for Robust LLM Security [13.404415593709986]
  Adrialversa Prompt Disentanglement (APD) framework identifies and neutralizes malicious components in input prompts before they are processed by the Large Language Models.<n>APD reduces harmful output generation by over 85% while maintaining negligible impact on model performance.<n>Our work addresses critical challenges in machine learning security on novel attacks and integrity methods for ML systems.
  arXiv  Detail & Related papers  (2026-05-27T01:30:06Z)
• Robust Multimodal Safety via Conditional Decoding [52.92816441364308]
  Multimodal large-language models (MLLMs) often experience degraded safety alignment when harmful queries exploit cross-modal interactions.<n>We propose a simple conditional decoding strategy, CASA, that utilizes internal representations of MLLMs to predict a binary safety token before response generation.
  arXiv  Detail & Related papers  (2026-03-31T23:19:50Z)
• Enhancing Safety of Large Language Models via Embedding Space Separation [24.821172423424866]
  Large language models (LLMs) have achieved impressive capabilities, yet ensuring their safety against harmful prompts remains a critical challenge.<n>Recent work has revealed that the latent representations (embeddings) of harmful and safe queries in LLMs typically exhibit linear separability.<n>Motivated by this observation, we propose a representation-level fine-tuning approach, named Embedding Space Separation (ES2)
  arXiv  Detail & Related papers  (2026-03-01T07:22:38Z)
• LVD-GS: Gaussian Splatting SLAM for Dynamic Scenes via Hierarchical Explicit-Implicit Representation Collaboration Rendering [21.615484471658842]
  3D Gaussian Splatting SLAM has emerged as a widely used technique for high-fidelity mapping in spatial intelligence.<n>Existing methods often rely on a single representation scheme, which limits their performance in large-scale dynamic outdoor scenes.<n>We propose textbfLVD-GS, a novel LiDAR-Visual 3D Gaussian Splatting SLAM system.
  arXiv  Detail & Related papers  (2025-10-26T13:16:39Z)
• DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models [50.21378052667732]
  We conduct an in-depth analysis of dLLM vulnerabilities to jailbreak attacks across two distinct dimensions: intra-step and inter-step dynamics.<n>We propose DiffuGuard, a training-free defense framework that addresses vulnerabilities through a dual-stage approach.
  arXiv  Detail & Related papers  (2025-09-29T05:17:10Z)
• D-REX: A Benchmark for Detecting Deceptive Reasoning in Large Language Models [62.83226685925107]
  Deceptive Reasoning Exposure Suite (D-REX) is a novel dataset designed to evaluate the discrepancy between a model's internal reasoning process and its final output.<n>Each sample in D-REX contains the adversarial system prompt, an end-user's test query, the model's seemingly innocuous response, and, crucially, the model's internal chain-of-thought.<n>We demonstrate that D-REX presents a significant challenge for existing models and safety mechanisms.
  arXiv  Detail & Related papers  (2025-09-22T15:59:40Z)
• Automating Steering for Safe Multimodal Large Language Models [58.36932318051907]
  We introduce a modular and adaptive inference-time intervention technology, AutoSteer, without requiring any fine-tuning of the underlying model.<n>AutoSteer incorporates three core components: (1) a novel Safety Awareness Score (SAS) that automatically identifies the most safety-relevant distinctions among the model's internal layers; (2) an adaptive safety prober trained to estimate the likelihood of toxic outputs from intermediate representations; and (3) a lightweight Refusal Head that selectively intervenes to modulate generation when safety risks are detected.
  arXiv  Detail & Related papers  (2025-07-17T16:04:55Z)
• SAFER: Probing Safety in Reward Models with Sparse Autoencoder [13.390179692415233]
  We present sparse Autoencoder For Enhanced Reward model (textbfSAFER)<n>We uncover human-interpretable features in reward model activations, enabling insight into safety-relevant decision-making.<n>Experiments show that SAFER can precisely degrade or enhance safety alignment with minimal data modification.
  arXiv  Detail & Related papers  (2025-07-01T11:04:03Z)
• SoK: Prompt Hacking of Large Language Models [5.056128048855064]
  The safety and robustness of large language models (LLMs) based applications remain critical challenges in artificial intelligence. We offer a comprehensive and systematic overview of three distinct types of prompt hacking: jailbreaking, leaking, and injection. We propose a novel framework that categorizes LLM responses into five distinct classes, moving beyond the traditional binary classification.
  arXiv  Detail & Related papers  (2024-10-16T01:30:41Z)
• What Makes and Breaks Safety Fine-tuning? A Mechanistic Study [64.9691741899956]
  Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. We design a synthetic data generation framework that captures salient aspects of an unsafe input. Using this, we investigate three well-known safety fine-tuning methods.
  arXiv  Detail & Related papers  (2024-07-14T16:12:57Z)
• RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content [62.685566387625975]
  Current mitigation strategies, while effective, are not resilient under adversarial attacks. This paper introduces Resilient Guardrails for Large Language Models (RigorLLM), a novel framework designed to efficiently moderate harmful and unsafe inputs.
  arXiv  Detail & Related papers  (2024-03-19T07:25:02Z)
• On Prompt-Driven Safeguarding for Large Language Models [172.13943777203377]
  We find that in the representation space, the input queries are typically moved by safety prompts in a "higher-refusal" direction. Inspired by these findings, we propose a method for safety prompt optimization, namely DRO. Treating a safety prompt as continuous, trainable embeddings, DRO learns to move the queries' representations along or opposite the refusal direction, depending on their harmfulness.
  arXiv  Detail & Related papers  (2024-01-31T17:28:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.