Trojan-Speak: Bypassing Constitutional Classifiers with No Jailbreak Tax via Adversarial Finetuning

摘要

Fine-tuning APIs offered by major AI providers create new attack surfaces where adversaries can bypass safety measures through targeted fine-tuning. We introduce **Trojan-Speak**, an adversarial fine-tuning method that bypasses Anthropic's Constitutional Classifiers. Our approach uses curriculum learning combined with GRPO-based hybrid reinforcement learning to teach models a communication protocol that evades LLM-based content classification. Crucially, while prior adversarial fine-tuning approaches report more than 25\% capability degradation on reasoning benchmarks, Trojan-Speak incurs less than 5\% degradation while achieving 99+\% classifier evasion for models with 14B+ parameters. We demonstrate that fine-tuned models can provide detailed responses to expert-level CBRN (Chemical, Biological, Radiological, and Nuclear) queries from Anthropic's Constitutional Classifiers bug-bounty program. Our findings reveal that LLM-based content classifiers alone are insufficient for preventing dangerous information disclosure when adversaries have fine-tuning access, and we show that activation-level probes can substantially improve robustness to such attacks.