Robustness

Bridging the Theoretical Gap in Randomized Smoothing AISTATS 2025 Cocktail-Party Audio-Visual Speech Recognition Interspeech 2025 Corruption Robust Offline Reinforcement Learning with Human Feedback AISTATS 2025 From Sharpness to Better Generalization for Speech Deepfake Detection Interspeech 2025 Gain from Neighbors: Boosting Model Robustness in the Wild via Adversarial Perturbations Toward Neighboring Classes CVPR 2025 Hearing deficits of transformer-based ASR for anechoic and spatial signals Interspeech 2025 Keeping up with dynamic attackers: Certifying robustness to adaptive online data poisoning AISTATS 2025 LID Models are Actually Accent Classifiers: Implications and Solutions for LID on Accented Speech Interspeech 2025 LR0.FM: Low-Res Benchmark and Improving robustness for Zero-Shot Classification in Foundation Models ICLR 2025 Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learning ICLR 2025 On Minimizing Adversarial Counterfactual Error in Adversarial Reinforcement Learning ICLR 2025 On the Difficulty of Constructing a Robust and Publicly-Detectable Watermark AISTATS 2025 On the Relationship Between Robustness and Expressivity of Graph Neural Networks AISTATS 2025 Out-of-distribution Robust Optimization UAI 2025 Probing the Robustness Properties of Neural Speech Codecs Interspeech 2025 RDI: An adversarial robustness evaluation metric for deep neural networks based on model statistical features UAI 2025 Relaxed Transition Kernels can Cure Underestimation in Adversarial Offline Reinforcement Learning ACML 2025 Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning ICLR 2025 Single-agent Poisoning Attacks Suffice to Ruin Multi-Agent Learning ICLR 2025 Speech Robust Bench: A Robustness Benchmark For Speech Recognition ICLR 2025 Subspace Recovery in Winsorized PCA: Insights into Accuracy and Robustness AISTATS 2025 VoiceNoNG: Robust High-Quality Speech Editing Model without Hallucinations Interspeech 2025 Adversarial Training Should Be Cast as a Non-Zero-Sum Game ICLR 2024 Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies ICLR 2024 Can we Defend Against the Unknown? An Empirical Study About Threshold Selection for Neural Network Monitoring UAI 2024