Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis

• URL: http://arxiv.org/abs/2605.11664v1
• Date: Tue, 12 May 2026 07:23:02 GMT
• Title: Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis
• Abstract summary: Large Reasoning Models (LRMs) improve performance on complex tasks, but they also make safety control harder at deployment time.<n>In black-box settings, defenders cannot modify model weights and must instead intervene at inference time.<n>This setting creates three practical challenges: harmful intent may be hidden by educational or role-play framing, deep safety analysis can introduce non-trivial latency, and long adversarial contexts can dilute the local cues that simpler filters rely on.<n>We propose Safety Context Injection (SCI), an inference-time framework that separates safety assessment from task generation and prepends a structured external risk report as injected safety context for the protected
• Score: 18.33590637095743
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Reasoning Models (LRMs) improve performance on complex tasks, but they also make safety control harder at deployment time. In black-box settings, defenders cannot modify model weights and must instead intervene at inference time. This setting creates three practical challenges: harmful intent may be hidden by educational or role-play framing, deep safety analysis can introduce non-trivial latency, and long adversarial contexts can dilute the local cues that simpler filters rely on. These challenges can expose an apparent thinking--output gap, where the model appears cautious during reasoning but still produces an unsafe final answer. To address this problem, we propose Safety Context Injection (SCI), an inference-time framework that separates safety assessment from task generation and prepends a structured external risk report as injected safety context for the protected model. The framework is instantiated in two complementary variants: Static Model Filtering (SMF), a lightweight one-pass guard for fast deployment, and Dynamic Agents Filtering (DAF), an agentic-loop-based analyzer that iteratively gathers and synthesizes evidence for ambiguous or long-context attacks. Across AdvBench and GPTFuzz, spanning base and reasoning models under five jailbreak families, both variants reduce attack success rate and toxicity in the evaluated settings. SMF offers an efficient low-latency option, while DAF is more effective when harmful intent is semantically disguised or dispersed across long contexts.

Related papers

• Furina: Fragmented Uncertainty-Driven Refusal Instability Attack [9.678677899786718]
  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.
  arXiv  Detail & Related papers  (2026-05-24T11:35:12Z)
• Selective Safety Steering via Value-Filtered Decoding [54.87935112120107]
  Large language models (LLMs) are trained to align with human values, but their generations may still violate safety constraints.<n>Existing decoding-time steering methods often intervene unnecessarily, modifying generations that would have been safe under the base model.<n>We propose a new test-time steering method designed to reduce such unnecessary interventions while improving the safety of unsafe responses.
  arXiv  Detail & Related papers  (2026-05-14T12:13:08Z)
• RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs [5.100622189286672]
  Fine-tuning safety-aligned language models for downstream tasks can lead to substantial degradation of refusal behavior.<n>We introduce REFUSALGUARD, a representation-level fine-tuning framework that preserves safety-relevant structure during model adaptation.
  arXiv  Detail & Related papers  (2026-05-03T14:48:18Z)
• 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)
• ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack [52.17935054046577]
  We present ReasAlign, a model-level solution to improve safety alignment against indirect prompt injection attacks.<n>ReasAlign incorporates structured reasoning steps to analyze user queries, detect conflicting instructions, and preserve the continuity of the user's intended tasks.
  arXiv  Detail & Related papers  (2026-01-15T08:23:38Z)
• VIGIL: Defending LLM Agents Against Tool Stream Injection via Verify-Before-Commit [44.24310459184061]
  LLM agents operating in open environments face escalating risks from indirect prompt injection.<n>We propose textbfVIGIL, a framework that shifts the paradigm from restrictive isolation to a verify-before-commit protocol.
  arXiv  Detail & Related papers  (2026-01-09T12:19:49Z)
• RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic [56.38397499463889]
  Embodied agents powered by vision-language models (VLMs) are increasingly capable of executing complex real-world tasks.<n>However, they remain vulnerable to hazardous instructions that may trigger unsafe behaviors.<n>We propose RoboSafe, a runtime safeguard for embodied agents through executable predicate-based safety logic.
  arXiv  Detail & Related papers  (2025-12-24T15:01:26Z)
• EASE: Practical and Efficient Safety Alignment for Small Language Models [4.839980912290382]
  Small language models (SLMs) are increasingly deployed on edge devices, making their safety alignment crucial yet challenging.<n>We propose EASE, a novel framework that enables practical and Efficient safety alignment for Small languagE models.
  arXiv  Detail & Related papers  (2025-11-09T19:46:54Z)
• 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)
• Shape it Up! Restoring LLM Safety during Finetuning [65.75757313781104]
  Finetuning large language models (LLMs) enables user-specific customization but introduces critical safety risks.<n>We propose dynamic safety shaping (DSS), a framework that uses fine-grained safety signals to reinforce learning from safe segments of a response while suppressing unsafe content.<n>We present STAR-DSS, guided by STAR scores, that robustly mitigates finetuning risks and delivers substantial safety improvements across diverse threats, datasets, and model families.
  arXiv  Detail & Related papers  (2025-05-22T18:05:16Z)
• Advancing Neural Network Verification through Hierarchical Safety Abstract Interpretation [52.626086874715284]
  We introduce a novel problem formulation called Abstract DNN-Verification, which verifies a hierarchical structure of unsafe outputs.<n>By leveraging abstract interpretation and reasoning about output reachable sets, our approach enables assessing multiple safety levels during the formal verification process.<n>Our contributions include a theoretical exploration of the relationship between our novel abstract safety formulation and existing approaches.
  arXiv  Detail & Related papers  (2025-05-08T13:29:46Z)
• 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.