{"total":16,"rows":[{"id":"2510.18214","title":"VLSU: Mapping the Limits of Joint Multimodal Understanding for AI Safety","created":"2025-10-21","cited_by_count":8,"area":null},{"id":"2512.23573","title":"ProGuard: Towards Proactive Multimodal Safeguard","created":"2025-12-29","cited_by_count":4,"area":null},{"id":"2506.09827","title":"EmoNet-Voice: A Fine-Grained, Expert-Verified Benchmark for Speech Emotion Detection","created":"2025-06-11","cited_by_count":3,"area":null},{"id":"2510.21120","title":"SafetyPairs: Isolating Safety Critical Image Features with Counterfactual Image Generation","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2605.07760","title":"RuleSafe-VL: Evaluating Rule-Conditioned Decision Reasoning in Vision-Language Content Moderation","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2608.05210","title":"Innocent Panels, Hateful Stories: Evaluating and Detecting Hateful Intent in Multi-Turn Visual Story Generation","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2604.06063","title":"EDGE-Shield: Efficient Denoising-staGE Shield for Violative Content Filtering via Scalable Reference-Based Matching","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2604.08819","title":"SenBen: Sensitive Scene Graphs for Explainable Content Moderation","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.12876","title":"Certified Robustness under Heterogeneous Perturbations via Hybrid Randomized Smoothing","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.28137","title":"No Safe Dose: How Training Data Drives Unsafe Image Generation","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.25034","title":"Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2607.00576","title":"Safe Alone, Unsafe Together: Safeguarding Against Implicit Toxicity When Benign Images Combine","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.24898","title":"Harm is not Universal: Community-Specific Toxicity Detection is Urgently Needed","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2609.18328","title":"Visual Compliance via Executable Safety Rule Entailment","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.32016","title":"VoiceNet: Fine-Grained Voice Understanding Beyond Emotion at Scale","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2610.11286","title":"When Scene Text Hijacks the Scene: Uncovering, Exploiting, and Mitigating Rendered-Text Semantic Leakage in Image Generation Models","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}