LoRA-Patch: Defending Against Backdoored LoRA Adapters via Directional Steering
cs.CR, cs.AI
Submitted: 2026-11-02
Updated: 2026-11-02
Code: https://github.com/FOXVEDA/LoRA-Patch
Terminology
Sources
- Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
- Training Verifiers to Solve Math Word Problems
- The Llama 3 Herd of Models
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
- Mistral 7B
- Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks
- CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization
- Steering Language Models With Activation Engineering
- PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models
- LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation
- Universal and Transferable Adversarial Attacks on Aligned Language Models
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data