REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak

• URL: http://arxiv.org/abs/2605.20654v1
• Date: Wed, 20 May 2026 03:16:15 GMT
• Title: REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak
• Abstract summary: Large Language Models (LLMs) are susceptible to sophisticated, multi-step jailbreak attacks.<n>We propose a principled two-stage framework that internalizes self-reflection within the generation trajectory.
• Score: 17.68660005545745
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While Large Language Models (LLMs) demonstrate remarkable capabilities, they remain susceptible to sophisticated, multi-step jailbreak attacks that circumvent conventional surface-level safety alignment by exploiting the internal generation process. To address these vulnerabilities, we propose Reflector, a principled two-stage framework that internalizes self-reflection within the generation trajectory. Reflector first leverages teacher-guided generation to produce high-quality reflection data for supervised fine-tuning (SFT), establishing structured reflection patterns. It subsequently uses Reinforcement Learning (RL) with outcome-driven and reward-validity supervision to instill robust, autonomous self-reflection capabilities. Empirical results show that Reflector achieves Defense Success Rates (DSR) exceeding 90% against complex indirect attacks while generalizing robustly across diverse threat scenarios. Notably, the framework enhances both task-specific and general utility, yielding a 5.85% gain on GSM8K alongside improved performance on knowledge-intensive benchmarks. By internalizing trajectory-level safety, Reflector overcomes the fundamental limitations of surface alignment without significant computational overhead, offering an efficient and scalable solution for the development of safe and capable LLMs.

Related papers

• Steering LLM Viewpoints through Fabricated Evidence Injection [61.22850755490993]
  We introduce a two-phase attack framework that first repackages misleading statements with fabricated rationales, then instruct target LLMs to incorporate these viewpoints when responding to relevant queries.<n>Experiments on BBQ, ToxiGen, and our specialized dataset reveal that commercial LLMs without external safety classifiers remain highly vulnerable.<n>Building on this, we explore multiple defense strategies, among which a tailored safety policy enablesgpt-oss-safeguard to achieve 81% detection rate.
  arXiv  Detail & Related papers  (2026-06-04T14:48:23Z)
• RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs [9.24144060095413]
  We present RouteHijack, a routing-aware jailbreak for large language models (LLMs)<n> RouteHijack performs response-driven expert localization to identify safety-critical and harmful experts.<n>It then constructs adversarial suffixes with a routing-aware objective that suppresses safety experts, promotes harmful experts, and prevents early-stage refusal.
  arXiv  Detail & Related papers  (2026-05-01T11:54:55Z)
• Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models [62.16655896700062]
  Activation steering is a technique to enhance the utility of Large Language Models (LLMs)<n>We show that it unintentionally introduces critical and under-explored safety risks.<n>Experiments reveal that these interventions act as a force multiplier, creating new vulnerabilities to jailbreaks and increasing attack success rates to over 80% on standard benchmarks.
  arXiv  Detail & Related papers  (2026-02-03T12:32:35Z)
• Self-Guard: Defending Large Reasoning Models via enhanced self-reflection [54.775612141528164]
  Self-Guard is a lightweight safety defense framework for Large Reasoning Models.<n>It bridges the awareness-compliance gap, achieving robust safety performance without compromising model utility.<n>Self-Guard exhibits strong generalization across diverse unseen risks and varying model scales.
  arXiv  Detail & Related papers  (2026-01-31T13:06:11Z)
• Think-Reflect-Revise: A Policy-Guided Reflective Framework for Safety Alignment in Large Vision Language Models [58.17589701432514]
  Think-Reflect-Revise (TRR) is a training framework designed to enhance the safety alignment of Large Vision Language Models (LVLMs)<n>We first build a Reflective Safety Reasoning (ReSafe) dataset with 5,000 examples that follow a think-reflect-revise process.<n>We then fine-tune the target model using the ReSafe dataset to initialize reflective behavior, and finally reinforce policy-guided reflection through reinforcement learning.
  arXiv  Detail & Related papers  (2025-12-08T03:46:03Z)
• Breaking the Safety-Capability Tradeoff: Reinforcement Learning with Verifiable Rewards Maintains Safety Guardrails in LLMs [3.198812241868092]
  reinforcement learning with verifiable rewards (RLVR) has emerged as a promising alternative that optimize models on objectively measurable tasks.<n>We present the first comprehensive theoretical and empirical analysis of safety properties in RLVR.<n> Empirically, we conduct extensive experiments across five adversarial safety benchmarks, demonstrating that RLVR can simultaneously enhance reasoning capabilities while maintaining or improving safety guardrails.
  arXiv  Detail & Related papers  (2025-11-26T04:36:34Z)
• SAID: Empowering Large Language Models with Self-Activating Internal Defense [23.654016424365906]
  We introduce a new, training-free defense paradigm, Self-Activating Internal Defense (SAID)<n>SAID reframes the defense task from external correction to internal capability activation.<n>It substantially outperforms state-of-the-art defenses in reducing harmful outputs.
  arXiv  Detail & Related papers  (2025-10-23T02:07:54Z)
• RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization [111.1749164063616]
  We propose RL-PLUS, a novel hybrid-policy optimization approach for Large Language Models (LLMs)<n> RL-PLUS synergizes internal exploitation with external data to achieve stronger reasoning capabilities and surpass the boundaries of base models.<n>We provide both theoretical analysis and extensive experiments to demonstrate the superiority and generalizability of our approach.
  arXiv  Detail & Related papers  (2025-07-31T23:55:29Z)
• Improving LLM Safety Alignment with Dual-Objective Optimization [81.98466438000086]
  Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks.<n>We propose an improved safety alignment that disentangles DPO objectives into two components: (1) robust refusal training, which encourages refusal even when partial unsafe generations are produced, and (2) targeted unlearning of harmful knowledge.
  arXiv  Detail & Related papers  (2025-03-05T18:01:05Z)
• Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking [54.10710423370126]
  We propose Reasoning-to-Defend (R2D), a training paradigm that integrates a safety-aware reasoning mechanism into Large Language Models' generation process.<n>CPO enhances the model's perception of the safety status of given dialogues.<n>Experiments demonstrate that R2D effectively mitigates various attacks and improves overall safety, while maintaining the original performances.
  arXiv  Detail & Related papers  (2025-02-18T15:48:46Z)
• TrustRAG: Enhancing Robustness and Trustworthiness in Retrieval-Augmented Generation [31.231916859341865]
  TrustRAG is a framework that systematically filters malicious and irrelevant content before it is retrieved for generation.<n>TrustRAG delivers substantial improvements in retrieval accuracy, efficiency, and attack resistance.
  arXiv  Detail & Related papers  (2025-01-01T15:57:34Z)

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.