SafetyMem: Adaptive Jailbreak Defense via Dual-Component Safety Memory

ACL ARR 2026 January Submission4644 Authors

Keywords: LLM safety; LLM memory

Abstract: Current defenses for Large Language Models (LLMs) often suffer from a ''memory gap'': parameter-modifying methods are computationally rigid, while inference-time filters cannot retain or reuse defense knowledge across interactions. To address this, we propose SafetyMem, a novel framework that secures LLMs through a dual-component safety memory system. SafetyMem consists of Semantic Safety Memory (SSM), which consolidates diverse jailbreak attempts into a structured knowledge base of attack patterns, and Episodic Safety Memory (ESM), which maintains an evolving set of procedural rules refined from historical detection failures. Unlike static defenses, SafetyMem allows the model to ''remember'' and adapt to emerging adversarial strategies without parameter retraining. To further enhance robustness, we introduce an adversarial memory expansion mechanism that proactively generates challenging variants to solidify these memories. Experiments on standard and stealthy jailbreak benchmarks show that SafetyMem substantially reduces attack success rates while preserving efficiency and interpretability, consistently outperforming state-of-the-art baselines across multiple LLMs.

Paper Type: Long

Research Area: Safety and Alignment in LLMs

Research Area Keywords: safety and alignment

Contribution Types: Model analysis & interpretability, NLP engineering experiment

Languages Studied: English

Submission Number: 4644