NeurIPS 2024 Workshop SafeGenAi Submissions

Smoothed Embeddings for Robust Language Models
Ryo Hase, Md Rafi Ur Rashid, Ashley Lewis, Jing Liu, Toshiaki Koike-Akino, Kieran Parsons, Ye Wang
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Investigating LLM Memorization: Bridging Trojan Detection and Training Data Extraction
Manoj Acharya, Xiao Lin, Susmit Jha
- Published: 12 Oct 2024, Last Modified: 21 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Testing the Limits of Jailbreaking Defenses with the Purple Problem
Taeyoun Kim, Suhas Kotha, Aditi Raghunathan
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
AEGIS2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails
Shaona Ghosh, Prasoon Varshney, Makesh Narsimhan Sreedhar, Aishwarya Padmakumar, Traian Rebedea, Jibin Rajan Varghese, Christopher Parisien
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Differentially Private Attention Computation
Yeqi Gao, Zhao Song, Xin Yang, Yufa Zhou
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Controllable Generation via Locally Constrained Resampling
Kareem Ahmed, Kai-Wei Chang, Guy Van den Broeck
- Published: 12 Oct 2024, Last Modified: 25 Nov 2024
- SafeGenAi Oral
- Readers: Everyone
RLHS: Mitigating Misalignment in RLHF with Hindsight Simulation
Kaiqu Liang, Haimin Hu, Ryan Liu, Thomas L. Griffiths, Jaime Fernández Fisac
- Published: 12 Oct 2024, Last Modified: 26 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
$\textit{Who Speaks Matters}$: Analysing the Influence of the Speaker’s Ethnicity on Hate Classification
Ananya Malik, Kartik Sharma, Lynnette Hui Xian Ng, Shaily Bhatt
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Oral
- Readers: Everyone
Honesty to Subterfuge: In-Context Reinforcement Learning Can Make Honest Models Reward Hack
Leo McKee-Reid, Christoph Sträter, Maria Angelica Martinez, Joe Needham, Mikita Balesni
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Decoding Diffusion: A Scalable Framework for Unsupervised Analysis of Latent Space Biases and Representations Using Natural Language Prompts
E. Zhixuan Zeng, Yuhao Chen, Alexander Wong
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
AnyPrefer: An Automatic Framework for Preference Data Synthesis
Yiyang Zhou, Zhaoyang Wang, Tianle Wang, Shangyu Xing, Peng Xia, Bo Li, Kaiyuan Zheng, Zijian Zhang, Zhaorun Chen, Wenhao Zheng, Xuchao Zhang, Chetan Bansal, Weitong Zhang, Ying Wei, Mohit Bansal, Huaxiu Yao
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Privacy-Preserving Large Language Model Inference via GPU-Accelerated Fully Homomorphic Encryption
Leo de Castro, Antigoni Polychroniadou, Daniel Escudero
- Published: 12 Oct 2024, Last Modified: 26 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Epistemic Integrity in Large Language Models
Bijean Ghafouri, Shahrad Mohammadzadeh, James Zhou, Pratheeksha Nair, Jacob-Junqi Tian, Mayank Goel, Reihaneh Rabbany, Jean-François Godbout, Kellin Pelrine
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
An Examination of AI-Generated Text Detectors Across Multiple Domains and Models
Brian Tufts, Xuandong Zhao, Lei Li
- Published: 12 Oct 2024, Last Modified: 19 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Towards Inference-time Category-wise Safety Steering for Large Language Models
Amrita Bhattacharjee, Shaona Ghosh, Traian Rebedea, Christopher Parisien
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Jogging the Memory of Unlearned LLMs Through Targeted Relearning Attacks
Shengyuan Hu, Yiwei Fu, Steven Wu, Virginia Smith
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Cream: Consistency Regularized Self-Rewarding Language Models
Zhaoyang Wang, Weilei He, Zhiyuan Liang, Xuchao Zhang, Chetan Bansal, Ying Wei, Weitong Zhang, Huaxiu Yao
- Published: 12 Oct 2024, Last Modified: 20 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
An Undetectable Watermark for Generative Image Models
Sam Gunn, Xuandong Zhao, Dawn Song
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Unlearning in- vs. out-of-distribution data in LLMs under gradient-based methods
Teodora Baluta, Pascal Lamblin, Daniel Tarlow, Fabian Pedregosa, Gintare Karolina Dziugaite
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs
Xuandong Zhao, Lei Li, Yu-Xiang Wang
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Large Language Model Benchmarks Do Not Test Reliability
Joshua Vendrow, Edward Vendrow, Sara Beery, Aleksander Madry
- Published: 12 Oct 2024, Last Modified: 17 Dec 2024
- SafeGenAi Poster
- Readers: Everyone
LLM Improvement for Jailbreak Defense: Analysis Through the Lens of Over-Refusal
Swetasudha Panda, Naveen Jafer Nizar, Michael L Wick
- Published: 12 Oct 2024, Last Modified: 26 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Shallow Diffuse: Robust and Invisible Watermarking through Low-Dimensional Subspaces in Diffusion Models
Wenda Li, Huijie Zhang, Qing Qu
- Published: 12 Oct 2024, Last Modified: 24 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Efficiently Identifying Watermarked Segments in Mixed-Source Texts
Xuandong Zhao, Chenwen Liao, Yu-Xiang Wang, Lei Li
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Language Models Can Articulate Their Implicit Goals
Jan Betley, Xuchan Bao, Martín Soto, Anna Sztyber-Betley, James Chua, Owain Evans
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone