Robustness

Safety Beyond the Training Data: Robust Out-of-Distribution MPC via Conformalized System Level Synthesis L4DC 2026 SafetyMem: Adaptive Jailbreak Defense via Dual-Component Safety Memory ACL 2026 Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination CVPR 2026 Scaling Test-Time Robustness of Vision-Language Models via Self-Critical Inference Framework CVPR 2026 SEBA: Sample-Efficient Black-Box Attacks on Visual Reinforcement Learning CVPR 2026 SEE: Signal Embedding Energy for Quantifying Noise Interference in Large Audio Language Models ACL 2026 Shedding Light on VLN Robustness: A Black-box Framework for Indoor Lighting-based Adversarial Attack CVPR 2026 Stable Language Guidance for Vision–Language–Action Models ACL 2026 Still Between Us? Evaluating and Improving Voice Assistant Robustness to Third-Party Interruptions ACL 2026 Sycophants in the Courtroom: Are LLMs Fragile to Juridical Authority and Evolving Legal Standards? ACL 2026 Teach a Reward Model to Correct Itself: Reward Guided Adversarial Failure Discovery for Robust Reward Modeling ACL 2026 Test-Time Perturbation Tuning with Delayed Feedback for Vision-Language-Action Models CVPR 2026 The Geometry of Robustness: Optimizing Loss Landscape Curvature and Feature Manifold Alignment for Robust Finetuning of Vision-Language Models CVPR 2026 Towards Reliable Evaluation of Adversarial Robustness for Spiking Neural Networks CVPR 2026 Truth or Sophistry? LoFa: A Benchmark for LLM Robustness Against Logical Fallacies ACL 2026 TTP: Test-Time Padding for Adversarial Detection and Robust Adaptation on Vision-Language Models CVPR 2026 Understanding the Prompt Sensitivity ACL 2026 Verifying Neural Network Robustness with Dual Perturbations CVPR 2026 What About the Scene With the Hitler Reference? HAUNT: A Framework to Probe LLMs’ Self-consistency in Closed Domains Via Adversarial Nudge ACL 2026 When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness CVPR 2026 When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical Pressure ACL 2026 X-AVDT: Audio-Visual Cross-Attention for Robust Deepfake Detection CVPR 2026 Adversaries With Incentives: A Strategic Alternative to Adversarial Robustness ICLR 2025 A High Dimensional Statistical Model for Adversarial Training: Geometry and Trade-Offs AISTATS 2025 A Robust Method to Discover Causal or Anticausal Relation ICLR 2025