arXiv (All)
open access
Membrane: A Self-Evolving Contrastive Safety Memory for LLM Agent Defense
Despite advances in safety alignment, large language models remain vulnerable to continuously evolving jailbreaks. Existing fine-tuned safety classifiers cannot adapt to these evolving attacks, while adaptive memory-based guardrails tend to over-refuse benign queries that resemble stored attacks. We
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Benign Inputs, Harmful Outputs: Cross-Modal Jailbreaking via Distributed Semantic Recomposition#246428
- Agent Safety From Within: Detecting Harmful Trajectories from LLM Internal States#1117751
- MemPoison: Bypassing Selective Memory Mechanisms to Plant Backdoors in LLM Agents#1118580
- Language-Based Agent Control#180601
- Semantic-TVM: Structure-Preserving Trustworthy Virtual Memory for Memory-Augmented and Tool-Using Agents#1084910
Record · ID 973202
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive