{"ID":2838867,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.15992","arxiv_id":"2511.15992","title":"Detecting Sleeper Agents in Large Language Models via Semantic Drift Analysis","abstract":"Large Language Models (LLMs) can be backdoored to exhibit malicious behavior under specific deployment conditions while appearing safe during training a phenomenon known as \"sleeper agents.\" Recent work by Hubinger et al. demonstrated that these backdoors persist through safety training, yet no practical detection methods exist. We present a novel dual-method detection system combining semantic drift analysis with canary baseline comparison to identify backdoored LLMs in real-time. Our approach uses Sentence-BERT embeddings to measure semantic deviation from safe baselines, complemented by injected canary questions that monitor response consistency. Evaluated on the official Cadenza-Labs dolphin-llama3-8B sleeper agent model, our system achieves 92.5% accuracy with 100% precision (zero false positives) and 85% recall. The combined detection method operates in real-time (\u003c1s per query), requires no model modification, and provides the first practical solution to LLM backdoor detection. Our work addresses a critical security gap in AI deployment and demonstrates that embedding-based detection can effectively identify deceptive model behavior without sacrificing deployment efficiency.","short_abstract":"Large Language Models (LLMs) can be backdoored to exhibit malicious behavior under specific deployment conditions while appearing safe during training a phenomenon known as \"sleeper agents.\" Recent work by Hubinger et al. demonstrated that these backdoors persist through safety training, yet no practical detection meth...","url_abs":"https://arxiv.org/abs/2511.15992","url_pdf":"https://arxiv.org/pdf/2511.15992v1","authors":"[\"Shahin Zanbaghi\",\"Ryan Rostampour\",\"Farhan Abid\",\"Salim Al Jarmakani\"]","published":"2025-11-20T02:42:41Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}