Security

Data-Driven and Stealthy Deactivation of Safety Filters L4DC 2025 Data Reconstruction Attacks and Defenses: A Systematic Evaluation AISTATS 2025 Defend for Self-Vocoding: A Novel Enhanced Decoder Network for Watermark Recovery Interspeech 2025 Defending Speech-enabled LLMs Against Adversarial Jailbreak Threats Interspeech 2025 Do You Steal My Model? Signature Diffusion Embedded Dual-Verification Watermarking for Protecting Intellectual Property of Hyperspectral Image Classification Models IJCAI 2025 EcoSafeRAG: Efficient Security through Context Analysis in Retrieval-Augmented Generation EMNLP 2025 EnvSDD: Benchmarking Environmental Sound Deepfake Detection Interspeech 2025 Evasion Attacks Against Bayesian Predictive Models UAI 2025 Exploiting Context-dependent Duration Features for Voice Anonymization Attack Systems Interspeech 2025 Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks ICLR 2025 Generalizable Audio Deepfake Detection via Hierarchical Structure Learning and Feature Whitening in Poincaré sphere Interspeech 2025 Generalizable Audio Spoofing Detection using Non-Semantic Representations Interspeech 2025 How to Recover Long Audio Sequences Through Gradient Inversion Attack With Dynamic Segment-based Reconstruction Interspeech 2025 Improving Adversarial Transferability via Decision Boundary Adaptation UAI 2025 Influence-Based Fair Selection for Sample-Discriminative Backdoor Attack AAAI 2025 J-SPAW: Japanese speaker verification and spoofing attacks recorded in-the-wild dataset Interspeech 2025 LitMAS: A Lightweight and Generalized Multi-Modal Anti-Spoofing Framework for Biometric Security Interspeech 2025 LRBA: Stealthy Backdoor Attacks on Speech Classification via Latent Rearrangement in VITS Interspeech 2025 Models That Are Interpretable But Not Transparent AISTATS 2025 On the Difficulty of Constructing a Robust and Publicly-Detectable Watermark AISTATS 2025 Poisoning Bayesian Inference via Data Deletion and Replication AISTATS 2025 Policy Teaching via Data Poisoning in Learning from Human Preferences AISTATS 2025 RepeatLeakage: Leak Prompts from Repeating as Large Language Model Is a Good Repeater AAAI 2025 Replay Attacks Against Audio Deepfake Detection Interspeech 2025 SAFE: Spiking Neural Network-based Audio Fidelity Evaluation ACML 2025