arXiv (All)
open access
Defending Against Malicious Finetuning by Scaling Train-time Adversarial Attacks
Malicious finetuning attacks pose a major safety threat against open-weight large language models (LLMs). However, existing alignment-stage defenses provide limited protection against strong attacks that use full-parameter finetuning. To address this issue, we propose Patcher, a novel and efficient
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
- Efficient LLM Adversarial Training via Low-Rank Defense and Circuit-Guided Surrogates#1116390
- Towards Effective Black-Box Adversarial Attacks on Deep Code Models via Structural and Identifier Perturbations#1062134
- A No-Defense Defense Against Gradient-Based Adversarial Attacks on ML-NIDS: Is Less More?#200374
- TAME: Token Attribution and Masking for Emergent misalignment#1122758
- ZOO: Zeroth Order Optimization Based Black-box Attacks to Deep Neural Networks without Training Substitute Models#19712
Record · ID 1117457
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