Lazare, veni foras: Reprogramming Dormant Neurons to Backdoor AI Agents
cs.CR, cs.AI, cs.LG
Submitted: 2026-11-11
Updated: 2026-11-11
Code: https://github.com/microsoft/lazarus
Terminology
Sources
- The Llama 3 Herd of Models
- SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge
- Agentic Backdoors via Pretraining Poisoning
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
- Sleeper Cell: Injecting Latent Malice Temporal Backdoors into Tool-Using LLMs
- Z-PEFT: Zero-shot Backdoor Detection in Parameter-Efficient Fine-Tuning via Canonical Spectral Signatures
- GLU Variants Improve Transformer
- Kerkoporta: Injecting Structured-Output Backdoors in Reasoning Coding Agents
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- Representation Engineering: A Top-Down Approach to AI Transparency
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