Furina: Fragmented Uncertainty-Driven Refusal Instability Attack

• URL: http://arxiv.org/abs/2605.26158v1
• Date: Sun, 24 May 2026 11:35:12 GMT
• Title: Furina: Fragmented Uncertainty-Driven Refusal Instability Attack
• Abstract summary: Safety alignment in large language models (LLMs) and multimodal large language models (MLLMs) is commonly assumed to operate as a near-binary threshold mechanism.<n>We challenge this assumption by revealing that safety behavior is governed by an instability region where small perturbations induce refusal decisions rather than deterministic outcomes.<n>We develop a multi-metric diagnostic framework combining external and internal signals to characterize this instability.<n>We introduce Furina, a jailbreak attack that deliberately induces this signature through fragmented, scene-anchored prompts without model-specific optimization.
• Score: 9.678677899786718
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Safety alignment in large language models (LLMs) and multimodal large language models (MLLMs) is commonly assumed to operate as a near-binary threshold mechanism. We challenge this assumption by revealing that safety behavior is governed by an instability region where small perturbations induce stochastic refusal decisions rather than deterministic outcomes. We develop a multi-metric diagnostic framework combining external and internal signals to characterize this instability. Through systematic experiments, we identify a characteristic diagnostic signature: inputs in unstable regimes exhibit elevated output uncertainty yet decreased internal safety activation, a decoupling phenomenon that explains why detection-based defenses fail against sophisticated attacks. Building on this framework, we introduce Furina, a jailbreak attack that deliberately induces this signature through fragmented, scene-anchored prompts without model-specific optimization. Furina outperforms strong single-turn and multi-turn baselines on HarmBench and achieves competitive results on MM-SafetyBench, demonstrating that uncertainty amplification provides a principled and transferable mechanism for understanding safety vulnerabilities. Code is available at: https://github.com/0xCavaliers/Furina_Jailbreak.

Related papers

• Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack [19.201635180438313]
  Large language models (LLMs) are rigorously aligned to refuse harmful requests.<n>In this work, we reveal that this advanced safety awareness inadvertently introduces a fatal vulnerability.
  arXiv  Detail & Related papers  (2026-06-04T02:36:41Z)
• Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy [51.758416625168]
  Randomized smoothing is a powerful tool for certifying robustness to adversarial perturbations.<n>We propose a framework for certification of complex, composed mechanisms.<n>We provide a principled and general framework for using composite mechanisms to certify robustness under complex threat models.
  arXiv  Detail & Related papers  (2026-05-20T22:17:29Z)
• Quantifiable Uncertainty: A Stochastic Consensus Multi-Agent RAG Framework for Robust Malware Detection [1.2183405753834562]
  We present MAGMA, a framework that decouples malware analysis into semantic code retrieval and probabilistic verification.<n>We show that MAGMA achieves a 98.4% detection rate, substantially exceeding existing solutions.
  arXiv  Detail & Related papers  (2026-05-08T18:46:24Z)
• Towards Trustworthy Depression Estimation via Disentangled Evidential Learning [50.22167852149165]
  We propose EviDep, an evidential learning framework that jointly quantifies depression severity.<n>EviDep enforces strict information integrity to guarantee robust evidence synthesis.<n>It achieves state-of-the-art predictive accuracy and superior uncertainty calibration, delivering a robust fail-safe mechanism for trustworthy clinical screening.
  arXiv  Detail & Related papers  (2026-04-17T13:27:11Z)
• 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)
• BarrierSteer: LLM Safety via Learning Barrier Steering [83.12893815611052]
  BarrierSteer is a novel framework that formalizes safety by embedding learned non-linear safety constraints directly into the model's latent representation space.<n>We show that BarrierSteer substantially reduces adversarial success rates, decreases unsafe generations, and outperforms existing methods.
  arXiv  Detail & Related papers  (2026-02-23T18:19:46Z)
• Fail-Closed Alignment for Large Language Models [4.205036273334146]
  We propose fail-closed alignment as a design principle for robust large language model safety.<n>We present a progressive alignment framework that iteratively identifies and ablates previously learned refusal directions.<n>Our mechanistic analyses confirm that models trained with our method encode multiple, causally independent refusal directions that prompt-based jailbreaks cannot suppress simultaneously.
  arXiv  Detail & Related papers  (2026-02-19T00:33:35Z)
• SafeThinker: Reasoning about Risk to Deepen Safety Beyond Shallow Alignment [43.86865924673546]
  We propose SafeThinker, an adaptive framework that allocates defensive resources via a lightweight gateway classifier.<n> Experiments show that SafeThinker significantly lowers attack success rates across diverse jailbreak strategies without compromising robustness.
  arXiv  Detail & Related papers  (2026-01-23T07:12:53Z)
• Agentic Uncertainty Quantification [76.94013626702183]
  We propose a unified Dual-Process Agentic UQ (AUQ) framework that transforms verbalized uncertainty into active, bi-directional control signals.<n>Our architecture comprises two complementary mechanisms: System 1 (Uncertainty-Aware Memory, UAM), which implicitly propagates verbalized confidence and semantic explanations to prevent blind decision-making; and System 2 (Uncertainty-Aware Reflection, UAR), which utilizes these explanations as rational cues to trigger targeted inference-time resolution only when necessary.
  arXiv  Detail & Related papers  (2026-01-22T07:16:26Z)
• 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)
• Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift [23.0914017433021]
  This work identifies a novel class of deployment phase attacks that exploit a vulnerability by injecting imperceptible perturbations directly into the embedding layer outputs without modifying model weights or input text.<n>We propose Search based Embedding Poisoning, a practical, model agnostic framework that introduces carefully optimized perturbations into embeddings associated with high risk tokens.
  arXiv  Detail & Related papers  (2025-09-08T05:00:58Z)
• Feature-Aware Malicious Output Detection and Mitigation [8.378272216429954]
  We propose a feature-aware method for harmful response rejection (FMM)<n>FMM detects the presence of malicious features within the model's feature space and adaptively adjusts the model's rejection mechanism.<n> Experimental results demonstrate the effectiveness of our approach across multiple language models and diverse attack techniques.
  arXiv  Detail & Related papers  (2025-04-12T12:12:51Z)

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.