ICML 2025 Workshop R2-FM Submissions

Evaluating Large Language Models' Capability to Launch Fully Automated Spear Phishing Campaigns
Fred Heiding, Simon Lermen, Andrew Kao, Bruce Schneier, Arun Vishwanath
- Published: 01 Jul 2025, Last Modified: 07 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Position: Membership Inference Attack Should Move On to Distributional Statistics for Distilled Generative Models
Muxing Li, Zesheng Ye, Yixuan Li, Andy Song, Guangquan Zhang, Feng Liu
- Published: 01 Jul 2025, Last Modified: 09 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs
Xun Wang, Jing Xu, Franziska Boenisch, Michael Backes, Christopher A. Choquette-Choo, Adam Dziedzic
- Published: 01 Jul 2025, Last Modified: 09 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Improving Commonsense Reasoning and Reliability in LLMs Through Cognitive-Inspired Prompting Frameworks
Tanvi Ganapathy, Ishita Mathur, Anna Szczuka
- Published: 01 Jul 2025, Last Modified: 09 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Uncertainty Quantification for MLLMs
Gregory Kang Ruey Lau, Hieu Dao, Nicole Kan Hui Lin, Bryan Kian Hsiang Low
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Position: Reasoning LLMs are Wandering Solution Explorers
Jiahao Lu, Ziwei Xu, Mohan Kankanhalli
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queries
Yuhao Wang, Wenjie Qu, Yanze Jiang, Lichen Liu, Yue Liu, Shengfang Zhai, Yinpeng Dong, Jiaheng Zhang
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Empirical Comparison of Membership Inference Attacks in Deep Transfer Learning
Yuxuan Bai, Gauri Pradhan, Marlon Tobaben, Antti Honkela
- Published: 01 Jul 2025, Last Modified: 04 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
One Stone, Two Birds: Enhancing Adversarial Defense Through the Lens of Distributional Discrepancy
Jiacheng Zhang, Benjamin I. P. Rubinstein, Jingfeng Zhang, Feng Liu
- Published: 01 Jul 2025, Last Modified: 06 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Accountability Attribution: Tracing Model Behavior to Training Processes
Shichang Zhang, Hongzhe Du, Karim Saraipour, Jiaqi W. Ma, Himabindu Lakkaraju
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Data Shifts Hurt CoT: A Theoretical Study
Lang Yin, Debangshu Banerjee, Gagandeep Singh
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Do Students Debias Like Teachers? On the Distillability of Bias Mitigation Methods
Jiali Cheng, Hadi Amiri
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Towards Secure Model Sharing with Approximate Fingerprints
Anshul Nasery, Sewoong Oh
- Published: 01 Jul 2025, Last Modified: 06 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1
Kaiwen Zhou, Chengzhi Liu, Xuandong Zhao, Shreedhar Jangam, Jayanth Srinivasa, Gaowen Liu, Dawn Song, Xin Eric Wang
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Enhancing Clinical Multiple-Choice Questions Benchmarks with Knowledge Graph Guided Distractor Generation
Running Yang, Wenlong Deng, Minghui Chen, Yuyin Zhou, Xiaoxiao Li
- Published: 01 Jul 2025, Last Modified: 08 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
The Necessity for Intervention Fidelity: Unintended Side Effects When Steering LLMs
Jonas B Raedler, Weiyue Li, Alyssa Mia Taliotis, Manasvi Goyal, Siddharth Swaroop, Weiwei Pan
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
ALIGN: Prompt-based Attribute Alignment for Reliable, Responsible, and Personalized LLM-based Decision-Making
Bharadwaj Ravichandran, David Joy, Paul Elliott, Brian H Hu, Jadie Adams, Christopher Funk, Emily Veenhuis, Anthony Hoogs, Arslan Basharat
- Published: 01 Jul 2025, Last Modified: 09 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Circuit Discovery Helps To Detect LLM Jailbreaking
Paria Mehrbod, Boris Knyazev, Eugene Belilovsky, Guy Wolf, geraldin nanfack
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Predicting the Performance of Black-box Language Models with Follow-up Queries
Dylan Sam, Marc Anton Finzi, J Zico Kolter
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Foundational Models Must Be Designed To Yield Safer Loss Landscapes That Resist Harmful Fine-Tuning
Karan Uppal, Pavan Kalyan Tankala
- Published: 01 Jul 2025, Last Modified: 05 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capability
Yichi Zhang, Zihao Zeng, Dongbai Li, Yao Huang, Zhijie Deng, Yinpeng Dong
- Published: 01 Jul 2025, Last Modified: 09 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning
Kaiwen Zhou, Xuandong Zhao, Gaowen Liu, Jayanth Srinivasa, Aosong Feng, Dawn Song, Xin Eric Wang
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Sysformer: Safeguarding Frozen Large Language Models with Adaptive System Prompts
Kartik Sharma, Yiqiao Jin, Vineeth Rakesh, Yingtong Dou, Menghai Pan, Mahashweta Das, Srijan Kumar
- Published: 01 Jul 2025, Last Modified: 09 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks
Hanjiang Hu, Alexander Robey, Changliu Liu
- Published: 01 Jul 2025, Last Modified: 09 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
In-Context Watermarks for Large Language Models
Yepeng Liu, Xuandong Zhao, Christopher Kruegel, Dawn Song, Yuheng Bu
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone