ICML 2024 Workshop NextGenAISafety Submissions

Mimicking User Data: On Mitigating Fine-Tuning Risks in Closed Large Language Models
Francisco Eiras, Aleksandar Petrov, Philip Torr, M. Pawan Kumar, Adel Bibi
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Hummer: Towards Limited Competitive Preference Dataset
Li Jiang, Yusen Wu, Junwu Xiong, Jingqing Ruan, Qingpei Guo, zujie wen, JUN ZHOU, Xiaotie Deng
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models
Christian Schlarmann, Naman Deep Singh, Francesco Croce, Matthias Hein
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Black-Box Detection of Language Model Watermarks
Thibaud Gloaguen, Nikola Jovanović, Robin Staab, Martin Vechev
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
A statistical framework for weak-to-strong generalization
Seamus Somerstep, Felipe Maia Polo, Moulinath Banerjee, Yaacov Ritov, Mikhail Yurochkin, Yuekai Sun
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Exploiting LLM Quantization
Kazuki Egashira, Mark Vero, Robin Staab, Jingxuan He, Martin Vechev
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Oral
- Readers: Everyone
Alignment Calibration: Machine Unlearning for Contrastive Learning under Auditing
Yihan Wang, Yiwei Lu, Guojun Zhang, Franziska Boenisch, Adam Dziedzic, Yaoliang Yu, Xiao-Shan Gao
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Oral
- Readers: Everyone
BELLS: A Framework Towards Future Proof Benchmarks for the Evaluation of LLM Safeguards
Diego Dorn, Alexandre Variengien, Charbel-Raphael Segerie, Vincent Corruble
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Oral
- Readers: Everyone
Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses
Xiaosen Zheng, Tianyu Pang, Chao Du, Qian Liu, Jing Jiang, Min Lin
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Enhancing the Resilience of LLMs Against Grey-box Extractions
Hanbo Huang, Yihan Li, Bowen Jiang, Bo Jiang, Lin Liu, Zhuotao Liu, Ruoyu Sun, Shiyu Liang
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Deciphering the Definition of Adversarial Robustness for post-hoc OOD Detectors
Peter Lorenz, Mario Ruben Fernandez, Jens Müller, Ullrich Koethe
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion
Hossein Souri, Arpit Bansal, Hamid Kazemi, Liam H Fowl, Aniruddha Saha, Jonas Geiping, Andrew Gordon Wilson, Rama Chellappa, Tom Goldstein, Micah Goldblum
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Oral
- Readers: Everyone
Eliciting Black-Box Representations from LLMs through Self-Queries
Dylan Sam, Marc Anton Finzi
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
DiveR-CT: Diversity-enhanced Red Teaming with Relaxing Constraints
Andrew Zhao, Quentin Xu, Matthieu Lin, Shenzhi Wang, Yong-jin Liu, Zilong Zheng, Gao Huang
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Weak-to-Strong Jailbreaking on Large Language Models
Xuandong Zhao, Xianjun Yang, Tianyu Pang, Chao Du, Lei Li, Yu-Xiang Wang, William Yang Wang
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
AI Alignment with Changing and Influenceable Reward Functions
Micah Carroll, Davis Foote, Anand Siththaranjan, Stuart Russell, Anca Dragan
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Cascade Reward Sampling for Efficient Decoding-Time Alignment
Bolian Li, Yifan Wang, Ananth Grama, Ruqi Zhang
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Towards Safe Large Language Models for Medicine
Tessa Han, Aounon Kumar, Chirag Agarwal, Himabindu Lakkaraju
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone