{"ID":5675139,"CreatedAt":"2026-07-03T01:40:09.565152011Z","UpdatedAt":"2026-07-05T05:29:26.995498422Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.01729","arxiv_id":"2607.01729","title":"DRL-CLBA: A Clean Label Backdoor Attack for Speech Classification via DDPG Reinforcement Learning","abstract":"Deep learning models for speech classification are vulnerable to backdoor attacks, where malicious triggers cause misclassification at inference time. While sample-specific attacks can bypass many defenses, they often rely on poisoned label attack, making them detectable via manual data defense. In this paper, we propose DRL-CLBA, a novel clean label backdoor attack for speech classification that leverages Deep Deterministic Policy Gradient (DDPG) reinforcement learning. We also utilize deep audio steganography to embed sample-specific triggers into source audio, creating feature-space anchors. The proposed reinforcement learning framework effectively optimizes target samples toward trigger-bearing anchor points in the model's deep latent space, enabling label-migration-free poisoning of target samples. Experimental results across three datasets and four different DNNs demonstrate that DRL-CLBA achieves a high attack success rate, effectively bypassing some backdoor defenses. The attack demonstrates strong resistance against fine-tuning, pruning, and spectral signature defenses, exposing critical vulnerabilities in speech-controlled systems.","short_abstract":"Deep learning models for speech classification are vulnerable to backdoor attacks, where malicious triggers cause misclassification at inference time. While sample-specific attacks can bypass many defenses, they often rely on poisoned label attack, making them detectable via manual data defense. In this paper, we propo...","url_abs":"https://arxiv.org/abs/2607.01729","url_pdf":"https://arxiv.org/pdf/2607.01729v1","authors":"[\"Yueming Huang\",\"Wenhan Yao\",\"Fen Xiao\",\"Xiarun Chen\",\"Weiping Wen\"]","published":"2026-07-02T05:34:20Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.SD\"]","methods":"[\"Reinforcement Learning\",\"Generative Adversarial Network\"]","has_code":false}