Safety Alignment Can Be Not Superficial With Explicit Safety Signals

• URL: http://arxiv.org/abs/2505.17072v2
• Date: Fri, 30 May 2025 05:54:56 GMT
• Title: Safety Alignment Can Be Not Superficial With Explicit Safety Signals
• Authors: Jianwei Li, Jung-Eun Kim,
• Abstract summary: Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially.<n>This paper identifies a fundamental cause of this superficiality: existing alignment approaches presume that models can implicitly learn a safety-related reasoning task during the alignment process.<n>By explicitly introducing a safety-related binary classification task and integrating its signals with our attention and decoding strategies, we eliminate this ambiguity.
• Score: 8.297367440457508
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies generally fail to offer actionable solutions beyond data augmentation for achieving more robust safety mechanisms. This paper identifies a fundamental cause of this superficiality: existing alignment approaches often presume that models can implicitly learn a safety-related reasoning task during the alignment process, enabling them to refuse harmful requests. However, the learned safety signals are often diluted by other competing objectives, leading models to struggle with drawing a firm safety-conscious decision boundary when confronted with adversarial attacks. Based on this observation, by explicitly introducing a safety-related binary classification task and integrating its signals with our attention and decoding strategies, we eliminate this ambiguity and allow models to respond more responsibly to malicious queries. We emphasize that, with less than 0.2x overhead cost, our approach enables LLMs to assess the safety of both the query and the previously generated tokens at each necessary generating step. Extensive experiments demonstrate that our method significantly improves the resilience of LLMs against various adversarial attacks, offering a promising pathway toward more robust generative AI systems.

Related papers

• ReGA: Representation-Guided Abstraction for Model-based Safeguarding of LLMs [0.9285458070502282]
  Large Language Models (LLMs) have achieved significant success in various tasks, yet concerns about their safety and security have emerged.<n>To analyze and monitor machine learning models, model-based analysis has demonstrated notable potential in stateful deep neural networks.<n>We propose ReGA, a model-based analysis framework with representation-guided abstraction, to safeguard LLMs against harmful prompts and generations.
  arXiv  Detail & Related papers  (2025-06-02T15:17:38Z)
• Learning Safety Constraints for Large Language Models [41.95596134688853]
  Large language models (LLMs) pose significant safety risks through harmful outputs and vulnerability to adversarial attacks.<n>We propose SaP, a geometric approach to safety that learns and enforces multiple safety constraints directly in the model's representation space.<n>We develop a framework that identifies safe and unsafe regions via the polytope's facets, enabling both detection and correction of unsafe outputs.
  arXiv  Detail & Related papers  (2025-05-30T10:30:24Z)
• Shape it Up! Restoring LLM Safety during Finetuning [66.46166656543761]
  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)
• SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning [76.56522719330911]
  Large Reasoning Models (LRMs) introduce a new generation paradigm of explicitly reasoning before answering.<n>LRMs pose great safety risks against harmful queries and adversarial attacks.<n>We propose SafeKey to better activate the safety aha moment in the key sentence.
  arXiv  Detail & Related papers  (2025-05-22T03:46:03Z)
• Representation Bending for Large Language Model Safety [27.842146980762934]
  Large Language Models (LLMs) have emerged as powerful tools, but their inherent safety risks pose significant challenges.<n>This paper introduces RepBend, a novel approach that fundamentally disrupts the representations underlying harmful behaviors in LLMs.<n>RepBend achieves state-of-the-art performance, outperforming prior methods such as Circuit Breaker, RMU, and NPO, with up to 95% reduction in attack success rates.
  arXiv  Detail & Related papers  (2025-04-02T09:47:01Z)
• SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering [56.92068213969036]
  Safety alignment is indispensable for Large Language Models (LLMs) to defend threats from malicious instructions.<n>Recent researches reveal safety-aligned LLMs prone to reject benign queries due to the exaggerated safety issue.<n>We propose a Safety-Conscious Activation Steering (SCANS) method to mitigate the exaggerated safety concerns.
  arXiv  Detail & Related papers  (2024-08-21T10:01:34Z)
• Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training [67.30423823744506]
  We introduce a novel approach, Decoupled Refusal Training (DeRTa), designed to empower LLMs to refuse compliance to harmful prompts at any response position.<n>DeRTa incorporates two novel components: (1) Maximum Likelihood Estimation with Harmful Response Prefix, which trains models to recognize and avoid unsafe content by appending a segment of harmful response to the beginning of a safe response, and (2) Reinforced Transition Optimization (RTO), which equips models with the ability to transition from potential harm to safety refusal consistently throughout the harmful response sequence.
  arXiv  Detail & Related papers  (2024-07-12T09:36:33Z)
• 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)
• The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness [56.174255970895466]
  Large Language Models (LLMs) play an increasingly pivotal role in natural language processing applications. This paper presents Safety and Over-Defensiveness Evaluation (SODE) benchmark.
  arXiv  Detail & Related papers  (2023-12-30T17:37:06Z)
• Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis [63.532413807686524]
  This paper addresses the problem of maintaining safety during training in Reinforcement Learning (RL) We propose a new architecture that handles the trade-off between efficient progress and safety during exploration.
  arXiv  Detail & Related papers  (2023-12-18T16:09:43Z)
• Lyapunov-based uncertainty-aware safe reinforcement learning [0.0]
  InReinforcement learning (RL) has shown a promising performance in learning optimal policies for a variety of sequential decision-making tasks. In many real-world RL problems, besides optimizing the main objectives, the agent is expected to satisfy a certain level of safety. We propose a Lyapunov-based uncertainty-aware safe RL model to address these limitations.
  arXiv  Detail & Related papers  (2021-07-29T13:08:15Z)

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.