论文解读
Quantum Kernels for Audio Deepfake Detection Using Spectrogram Patch Features
音频深度伪造检测 | 6.5/10
音频安全
论文解读
SEI-SHIELD: Robust Specific Emitter Identification Under Label Noise Via Self-Supervised Filtering and Iterative Rescue
信号处理 | 7.5/10
论文解读
Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization
音频安全 | 7.5/10
论文解读
DECKER: Domain-invariant Embedding for Cross-Keyboard Extraction and Recognition
音频安全 | 7.5/10
论文解读
Enhancing Self-Supervised Talking Head Forgery Detection via a Training-Free Dual-System Framework
说话头伪造检测 | 7.5/10
论文解读
MelShield: Robust Mel-Domain Audio Watermarking for Provenance Attribution of AI Generated Synthesized Speech
音频安全 | 7.0/10
会议任务专题
ICLR 2026 - 音频安全
共 1 篇 ICLR 2026 音频安全 方向论文
论文解读
JALMBench: Benchmarking Jailbreak Vulnerabilities in Audio Language Models
音频安全 | 8.0/10
论文解读
Are Deep Speech Denoising Models Robust to Adversarial Noise?
语音增强 | 7.5/10
论文解读
AudioTrust: Benchmarking The Multifaceted Trustworthiness of Audio Large Language Models
模型评估 | 8.5/10
论文解读
JALMBench: Benchmarking Jailbreak Vulnerabilities in Audio Language Models
音频安全 | 8.5/10
论文解读
A Feature-Optimized Audio Watermarking Algorithm with Adaptive Embedding Strength
音频安全 | 7.5/10
论文解读
Audio-Text Jailbreak Attack on Large Audio-Language Models: Towards Generality and Stealthiness
音频安全 | 7.0/10
论文解读
AURA: A Stegaformer-Based Scalable Deep Audio Watermark with Extreme Robustness
音频水印 | 7.5/10
论文解读
Bloodroot: When Watermarking Turns Poisonous for Stealthy Backdoor
音频安全 | 7.5/10
论文解读
Co-Initialization of Control Filter and Secondary Path via Meta-Learning for Active Noise Control
音频安全 | 7.5/10
论文解读
Cross-Domain Contrastive Learning with Dynamic Threshold Calibration for Source Speaker Tracing
说话人验证 | 8.0/10
论文解读
Disentangled Authenticity Representation for Partially Deepfake Audio Localization
音频深度伪造检测 | 6.5/10
论文解读
Emotional Damage: Investigating Safety Vulnerabilities of Large Audio-Language Models Under Speaker Emotional Variations
音频安全 | 7.5/10
论文解读
Erasing Your Voice Before it’s Heard: Training-Free Speaker Unlearning for Zero-Shot Text-to-Speech
语音合成 | 7.5/10