Mario Fritz

Deepfake Detection that Generalizes Across Benchmarks WACV 2026 Funny or Persuasive, but Not Both: Evaluating Fine-Grained Multi-Concept Control in LLMs EACL 2026 IV Co-Scientist: Multi-Agent LLM Framework for Causal Instrumental Variable Discovery CLeaR 2026 Accept or Deny? Evaluating LLM Fairness and Performance in Loan Approval across Table-to-Text Serialization Approaches EMNLP 2025 A Theory of Response Sampling in LLMs: Part Descriptive and Part Prescriptive ACL 2025 Automated Detection of Abnormalities in Zebrafish Development MICCAI 2025 Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation ACL 2025 Can LLMs Separate Instructions From Data? And What Do We Even Mean By That? ICLR 2025 CausalGraph2LLM: Evaluating LLMs for Causal Queries NAACL 2025 Context-Aware Reasoning On Parametric Knowledge for Inferring Causal Variables EMNLP 2025 DocMIA: Document-Level Membership Inference Attacks against DocVQA Models ICLR 2025 Medical Multimodal Model Stealing Attacks via Adversarial Domain Alignment AAAI 2025 Pixel-level Certified Explanations via Randomized Smoothing ICML 2025 Stealix: Model Stealing via Prompt Evolution ICML 2025 Adaptive Hierarchical Certification for Segmentation using Randomized Smoothing ICML 2024 Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation NeurIPS 2024 Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition NeurIPS 2024 Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models NeurIPS 2024 LLM Task Interference: An Initial Study on the Impact of Task-Switch in Conversational History EMNLP 2024 MultiMax: Sparse and Multi-Modal Attention Learning ICML 2024 On Adversarial Training without Perturbing all Examples ICLR 2024 PoLLMgraph: Unraveling Hallucinations in Large Language Models via State Transition Dynamics NAACL 2024 SimSCOOD: Systematic Analysis of Out-of-Distribution Generalization in Fine-tuned Source Code Models NAACL 2024 Stealthy Imitation: Reward-guided Environment-free Policy Stealing ICML 2024 B-Cos Networks: Alignment Is All We Need for Interpretability CVPR 2022 Open-Domain, Content-Based, Multi-Modal Fact-Checking of Out-of-Context Images via Online Resources CVPR 2022 Private Set Generation with Discriminative Information NeurIPS 2022 ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training ICML 2022 RelaxLoss: Defending Membership Inference Attacks without Losing Utility ICLR 2022 Responsible Disclosure of Generative Models Using Scalable Fingerprinting ICLR 2022 Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data ICCV 2021 Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis IJCAI 2021 Convolutional Dynamic Alignment Networks for Interpretable Classifications CVPR 2021 Dual Contrastive Loss and Attention for GANs ICCV 2021 Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers CVPR 2021 Future Moment Assessment for Action Query WACV 2021 Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs CVPR 2021 GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators NeurIPS 2020 Inclusive GAN: Improving Data and Minority Coverage in Generative Models ECCV 2020 Normalizing Flows With Multi-Scale Autoregressive Priors CVPR 2020 Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks ICLR 2020 Segmentations-Leak: Membership Inference Attacks and Defenses in Semantic Image Segmentation ECCV 2020 Towards Automated Testing and Robustification by Semantic Adversarial Data Generation ECCV 2020 Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing CVPR 2020 Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints ICCV 2019 Bayesian Prediction of Future Street Scenes using Synthetic Likelihoods ICLR 2019 Deep Appearance Maps ICCV 2019 Knockoff Nets: Stealing Functionality of Black-Box Models CVPR 2019 Not Using the Car to See the Sidewalk -- Quantifying and Controlling the Effects of Context in Classification and Segmentation CVPR 2019 Time-Conditioned Action Anticipation in One Shot CVPR 2019 Accurate and Diverse Sampling of Sequences Based on a “Best of Many” Sample Objective CVPR 2018 Adversarial Scene Editing: Automatic Object Removal from Weak Supervision NeurIPS 2018 A Hybrid Model for Identity Obfuscation by Face Replacement ECCV 2018 Connecting Pixels to Privacy and Utility: Automatic Redaction of Private Information in Images CVPR 2018 Disentangled Person Image Generation CVPR 2018 Diverse Conditional Image Generation by Stochastic Regression with Latent Drop-Out Codes ECCV 2018 Long-Term On-Board Prediction of People in Traffic Scenes Under Uncertainty CVPR 2018 Natural and Effective Obfuscation by Head Inpainting CVPR 2018 Towards Reverse-Engineering Black-Box Neural Networks ICLR 2018 A Domain Based Approach to Social Relation Recognition CVPR 2017 Adversarial Image Perturbation for Privacy Protection -- A Game Theory Perspective ICCV 2017 Exploiting Saliency for Object Segmentation From Image Level Labels CVPR 2017 Speaking the Same Language: Matching Machine to Human Captions by Adversarial Training ICCV 2017 STD2P: RGBD Semantic Segmentation Using Spatio-Temporal Data-Driven Pooling CVPR 2017 Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images ICCV 2017 What Is Around the Camera? ICCV 2017 Deep Reflectance Maps CVPR 2016 Multi-Cue Zero-Shot Learning With Strong Supervision CVPR 2016 Appearance-Based Gaze Estimation in the Wild CVPR 2015 Ask Your Neurons: A Neural-Based Approach to Answering Questions About Images ICCV 2015 Person Recognition in Personal Photo Collections ICCV 2015 Prediction of Search Targets From Fixations in Open-World Settings CVPR 2015 See the Difference: Direct Pre-Image Reconstruction and Pose Estimation by Differentiating HOG ICCV 2015 A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input NeurIPS 2014 Anytime Recognition of Objects and Scenes CVPR 2014 Image-based Synthesis and Re-Synthesis of Viewpoints Guided by 3D Models CVPR 2014 Multi-class Video Co-segmentation with a Generative Multi-video Model CVPR 2013 Sequential Bayesian Model Update under Structured Scene Prior for Semantic Road Scenes Labeling ICCV 2013 Timely Object Recognition NeurIPS 2012 Size Matters: Metric Visual Search Constraints from Monocular Metadata NeurIPS 2010 An Additive Latent Feature Model for Transparent Object Recognition NeurIPS 2009