ICML 2025 Past Generative models

Data in Generative Models - The Bad, the Ugly, and the Greats

DIG-BUG

Submission deadline
May 29, 2025, 12:00 UTC
imported from OpenReview — check the website for extensions
Submission portal
OpenReview
Notes
Auto-imported from the OpenReview venue record on 2026-06-10 — please verify and enrich (topics are keyword-guessed).

Accepted papers (37)

Fetched from OpenReview (v2) on 2026-06-10.

  1. A Data-Centric Safety Framework for Generative Models: Adversarial Fingerprint Detection and Attribution

    Dong Liu, Yanxuan Yu · PDF
  2. A Representation Engineering Perspective on the Effectiveness of Multi-Turn Jailbreaks

    Blake Bullwinkel, Mark Russinovich, Ahmed Salem, Santiago Zanella-Beguelin, Daniel Jones, Giorgio Severi, Eugenia Kim, Keegan Hines, Amanda J. Minnich, Yonatan Zunger, Ram Shankar Siva Kumar · PDF
  3. Backdooring VLMs via Concept-Driven Triggers

    Yufan Feng, Weimin Lyu, Yuxin Wang, Benjamin Tan, Yani Ioannou · PDF
  4. Both Text and Images Leaked! A Systematic Analysis of Data Contamination in Multimodal LLMs

    Dingjie Song, Sicheng Lai, Mingxuan Wang, Shunian Chen, Lichao Sun, Benyou Wang · PDF
  5. Cascading Adversarial Bias from Injection to Distillation in Language Models

    Harsh Chaudhari, Jamie Hayes, Matthew Jagielski, Ilia Shumailov, Milad Nasr, Alina Oprea · PDF
  6. COREVQA: A Crowd Observation and Reasoning Entailment Visual Question Answering Benchmark

    Charles Duong, Naaisha Agarwal, Ishant Yunay Chintapatla, Kazuma Choji, Andrew Lwin, Hannah You, Kevin Zhu, Sean O'Brien, Vasu Sharma · PDF
  7. Data Cartography for Detecting Memorization Hotspots and Guiding Data Interventions in Generative Models

    Laksh Patel, Neel N Shanbhag · PDF
  8. Detective SAM: Adapting SAM to Localize Diffusion-based Forgeries via Embedding Artifacts

    Gert Lek, Chaoyi Zhu, Pin-Yu Chen, Robert Birke, Lydia Y. Chen · PDF
  9. Diversity Boosts AI-Generated Text Detection

    Advik Raj Basani, Pin-Yu Chen · PDF
  10. DP-AdamW: Investigating Decoupled Weight Decay and Bias Correction in Private Deep Learning

    Lillian Sun, Kevin Cong, Je Qin Chooi, Russell Li · PDF
  11. FaceSafe: An Inpainting Pipeline for Privacy-Compliant Scalable Image Datasets

    Sydney Su, Lening Nick Cui, Ananya Salian, Roger You, Hao Qi Cui, Charles Duong, Kevin Zhu, Sean O'Brien, Vasu Sharma · PDF
  12. Firm Foundations for Membership Inference Attacks Against Large Language Models

    Jeffrey George Wang, Jason Wang, Marvin Li, Seth Neel · PDF
  13. Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models

    Lillian Sun, Martin Pawelczyk, Zhenting Qi, Aounon Kumar, Himabindu Lakkaraju · PDF
  14. Ghost in the Cloud: Your Geo-Distributed Large Language Models Training is Easily Manipulated

    Zichen TANG, Zhenheng Tang, Gaoning Pan, Buhua Liu, Kunfeng Lai, Xiaowen Chu, Bo Li · PDF
  15. Implementing Adaptations for Vision AutoRegressive Model

    Kaif Shaikh, Antoni Kowalczuk, Franziska Boenisch, Adam Dziedzic · PDF
  16. Improvement-Guided Iterative DPO for Diffusion Models

    Ying Fan, Fei Deng, Yang Zhao, Sahil Singla, Rahul Jain, Tingbo Hou, Kangwook Lee, Feng Yang, Deepak Ramachandran, Qifei Wang · PDF
  17. In-Context Bias Propagation in LLM-Based Tabular Data Generation

    Pol G. Recasens, Alberto Gutierrez-Torre, Jordi Torres, Josep Lluis Berral, Anisa Halimi, Kieran Fraser · PDF
  18. JailbreakLoRA: Your Downloaded LoRA from Sharing Platforms might be Unsafe

    Fanjunduo Wei, Zhenheng Tang, Rongfei Zeng, Tongliang Liu, Chengqi Zhang, Xiaowen Chu, Bo Han · PDF
  19. Layer-wise Influence Tracing: Data-Centric Mitigation of Memorization in Diffusion Models

    Thomas Y Chen · PDF
  20. Lookahead Bias in Pretrained Language Models

    Suproteem K Sarkar, Keyon Vafa · PDF
  21. MAD-MAX: Modular And Diverse Malicious Attack MiXtures for Automated LLM Red Teaming

    Stefan Schoepf, Muhammad Zaid Hameed, Ambrish Rawat, Kieran Fraser, Giulio Zizzo, Giandomenico Cornacchia, Mark Purcell · PDF
  22. Model-based Large Language Model Customization as Service

    Zhaomin Wu, Jizhou Guo, Junyi Hou, Bingsheng He, Lixin Fan, Qiang Yang · PDF
  23. Optimal Defenses Against Data Reconstruction Attacks

    Yuxiao Chen, Gamze Gursoy, Qi Lei · PDF
  24. Optimization and Robustness-Informed Membership Inference Attacks for LLMs

    Zichen Song, Qixin Zhang, Ming Li, Yao Shu · PDF
  25. OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models

    Ziheng Cheng, Yixiao Huang, Hui Xu, Somayeh Sojoudi, Xuandong Zhao, Dawn Song, Song Mei · PDF
  26. Preference Leakage: A Contamination Problem in LLM-as-a-judge

    Dawei Li, Renliang Sun, Yue Huang, Ming Zhong, Bohan Jiang, Jiawei Han, Xiangliang Zhang, Wei Wang, huan liu · PDF
  27. R&B: Breaking the Data Mixing Bottleneck with Just 0.01% Overhead

    Albert Ge, Tzu-Heng Huang, John Cooper, Avi Trost, Ziyi Chu, Satya Sai Srinath Namburi GNVV, Ziyang Cai, Kendall Park, Nicholas Roberts, Frederic Sala · PDF
  28. Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy

    Xiangru Tang, Kunlun Zhu, Tongxin Yuan, Yichi Zhang, Wangchunshu Zhou, Zhuosheng Zhang · PDF
  29. RN-F: A Novel Approach for Mitigating Contaminated Data in Large Language Models

    Le Vu Anh, Dinh Duc Nha Nguyen, Phi Long Nguyen, Keshav Sood · PDF
  30. SOSBENCH: Benchmarking Safety Alignment on Scientific Knowledge

    Fengqing Jiang, Fengbo Ma, Zhangchen Xu, Yuetai Li, Bhaskar Ramasubramanian, Luyao Niu, Bo Li, Xianyan Chen, Zhen Xiang, Radha Poovendran · PDF
  31. Spectral Manifold Harmonization for Graph Imbalanced Regression

    Brenda Nogueira, Meng Jiang, Nitesh V Chawla, Nuno Moniz · PDF
  32. Training Diffusion Models with Noisy Data via SFBD Flow

    Haoye Lu, Darren Lo, Yaoliang Yu · PDF
  33. TruthLens: Training-Free Data Verification for Deepfake Images via VQA-style Probing

    Ritabrata Chakraborty, Rajatsubhra Chakraborty, Ali Khaleghi Rahimian · PDF
  34. Unlocking Post-hoc Dataset Inference with Synthetic Data

    Bihe Zhao, Pratyush Maini, Franziska Boenisch, Adam Dziedzic · PDF
  35. Watermarking Image Autoregressive Models

    Michel Meintz, Jan Dubiński, Franziska Boenisch, Adam Dziedzic · PDF
  36. Weak-to-strong Generalization via Formative Learning from Student Demonstrations & Teacher Evaluation

    Nguyen Minh Phuc, Chinh Duc La, Heng Ji, Khoa D Doan · PDF
  37. Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets

    Lei Hsiung, Tianyu Pang, Yung-Chen Tang, Linyue Song, Tsung-Yi Ho, Pin-Yu Chen, Yaoqing Yang · PDF