Reinforcement Learning with Verifiable Rewards (RLVR) is an emerging paradigm that significantly boosts a Large Language Model's (LLM's) reasoning abilities on complex logical tasks, such as mathematics and programming.However, we identify, for the first time, a latent vulnerability to backdoor attacks within the RLVR framework.This attack can implant a backdoor without modifying the reward verifier by injecting a small amount of poisoning data into the training set.Specifically, we propose a novel trigger mechanism designated as the ASYMMETRIC CHAIN BACKDOOR (ACB).The attack exploits the RLVR training loop by assigning substantial positive rewards for harmful responses and negative rewards for refusals.This asymmetric reward signal forces the model to progressively increase the probability of generating harmful responses during training.Our findings demonstrate that the RLVR backdoor attack is characterized by both high efficiency and strong generalization capabilities.Utilizing less than 2% poisoned data in train set, the backdoor can be successfully implanted across various model scales without degrading performance on benign tasks.Evaluations across multiple jailbreak benchmarks indicate that activating the trigger degrades safety performance by an average of 73%.Furthermore, the attack generalizes effectively to a wide range of jailbreak methods and unsafe behaviors.

The proliferation of jailbreak attacks against large language models (LLMs) highlights the need for robust security measures.However, in multi-round dialogues, malicious intentions may be hidden in interactions, leading LLMs to be more prone to produce harmful responses.In this paper, we propose the Multi-Turn Safety Alignment (MTSA) framework, to address the challenge of securing LLMs in multi-round interactions.It consists of two stages: In the thought-guided attack learning stage, the redteam model learns about thought-guided multiround jailbreak attacks to generate adversarial prompts.In the adversarial iterative optimization stage, the red-team model and the target model continuously improve their respective capabilities in interaction.Furthermore, we introduce a multi-turn reinforcement learning algorithm based on future rewards to enhance the robustness of safety alignment.Experimental results show that the red-team model exhibits state-of-the-art attack capabilities, while the target model significantly improves its performance on safety benchmarks.