LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes
cs.CR, cs.AI, cs.CL
Submitted: 2026-08-07
Updated: 2026-10-26
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- The Llama 3 Herd of Models
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
- Occlusion-based Detection of Trojan-triggering Inputs in Large Language Models of Code
- CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization
- Large Language Models: A Survey
- LLaMA: Open and Efficient Foundation Language Models
- Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
- A Survey of Large Language Models
- A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Estimating the Social Cost of Corporate Data Breaches
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills