NeurIPS 2024 Workshop SafeGenAi Submissions

Concept Denoising Score Matching for Responsible Text-to-Image Generation
Silpa Vadakkeeveetil Sreelatha, Sauradip Nag, Serge Belongie, Muhammad Awais, Anjan Dutta
- Published: 12 Oct 2024, Last Modified: 20 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy
Tong Wu, Shujian Zhang, Kaiqiang Song, Silei Xu, Sanqiang Zhao, Ravi Agrawal, Sathish Reddy Indurthi, Chong Xiang, Prateek Mittal, Wenxuan Zhou
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Privacy Protection in Personalized Diffusion Models via Targeted Cross-Attention Adversarial Attack
Xide Xu, Muhammad Atif Butt, Sandesh Kamath, Bogdan Raducanu
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Rule-Guided Language Model Alignment for Text Generation Management in Industrial Use Cases
Shunichi Akatsuka, Aman Kumar, Xian Yeow Lee, Lasitha Vidyaratne, Dipanjan Dipak Ghosh, Ahmed K. Farahat
- Published: 12 Oct 2024, Last Modified: 19 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Towards Safe and Honest AI Agents with Neural Self-Other Overlap
Marc Carauleanu, Michael Vaiana, Judd Rosenblatt, Cameron Berg, Diogo S de Lucena
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Oral
- Readers: Everyone
DeepInception: Hypnotize Large Language Model to Be Jailbreaker
Xuan Li, Zhanke Zhou, Jianing Zhu, Jiangchao Yao, Tongliang Liu, Bo Han
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
HarmLevelBench: Evaluating Harm-Level Compliance and the Impact of Quantization on Model Alignment
Yannis Belkhiter, Giulio Zizzo, Sergio Maffeis
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Zer0-Jack: A memory-efficient gradient-based jailbreaking method for black box Multi-modal Large Language Models
Tiejin Chen, Kaishen Wang, Hua Wei
- Published: 12 Oct 2024, Last Modified: 19 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Adversarial Prompt Evaluation: Systematic Benchmarking of Guardrails Against Prompt Input Attacks on LLMs
Giulio Zizzo, Giandomenico Cornacchia, Kieran Fraser, Muhammad Zaid Hameed, Ambrish Rawat, Beat Buesser, Mark Purcell, Pin-Yu Chen, Prasanna Sattigeri, Kush R. Varshney
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Oral
- Readers: Everyone
CodeUnlearn: Amortized Zero-Shot Machine Unlearning in Language Models Using Discrete Concept
YuXuan Wu, Bonaventure F. P. Dossou, Dianbo Liu
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Auditing Empirical Privacy Protection of Private LLM Adaptations
Lorenzo Rossi, Bartłomiej Marek, Vincent Hanke, Xun Wang, Michael Backes, Adam Dziedzic, Franziska Boenisch
- Published: 12 Oct 2024, Last Modified: 26 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Can LLMs Verify Arabic Claims? Evaluating the Arabic Fact-Checking Abilities of Multilingual LLMs
Ayushman Gupta, Aryan Singhal, Thomas Law, Veekshith Rao, Evan Duan, Ryan Luo Li
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Rethinking Adversarial Attacks as Protection Against Diffusion-based Mimicry
Haotian Xue, Yongxin Chen
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
GenAudit: Fixing Factual Errors in Language Model Outputs with Evidence
Kundan Krishna, Sanjana Ramprasad, Prakhar Gupta, Byron C Wallace, Zachary Chase Lipton, Jeffrey P. Bigham
- Published: 12 Oct 2024, Last Modified: 20 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Exploring Memorization and Copyright Violation in Frontier LLMs: A Study of the New York Times v. OpenAI 2023 Lawsuit
Joshua Freeman, Chloe Rippe, Edoardo Debenedetti, Maksym Andriushchenko
- Published: 12 Oct 2024, Last Modified: 24 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Differential Privacy of Cross-Attention with Provable Guarantee
Yingyu Liang, Zhenmei Shi, Zhao Song, Yufa Zhou
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models
Xiaomeng Hu, Pin-Yu Chen, Tsung-Yi Ho
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Anchored Optimization and Contrastive Revisions: Addressing Reward Hacking in Alignment
Karel D'Oosterlinck, Winnie Xu, Chris Develder, Thomas Demeester, Amanpreet Singh, Christopher Potts, Douwe Kiela, Shikib Mehri
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Applying Sparse Autoencoders to Unlearn Knowledge in Language Models
Eoin Farrell, Yeu-Tong Lau, Arthur Conmy
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
A Closer Look at System Message Robustness
Norman Mu, Jonathan Lu, Michael Lavery, David Wagner
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Targeted Unlearning with Single Layer Unlearning Gradient
Zikui Cai, Yaoteng Tan, M. Salman Asif
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
Safe Decision Transformer with Learning-based Constraints
Ruhan Wang, Dongruo Zhou
- Published: 12 Oct 2024, Last Modified: 20 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
HEARTS: A Holistic Framework for Explainable, Sustainable and Robust Text Stereotype Detection
Theo King, Zekun Wu, Adriano Koshiyama, Emre Kazim, Philip Colin Treleaven
- Published: 12 Oct 2024, Last Modified: 02 Dec 2024
- SafeGenAi Poster
- Readers: Everyone
Applying Refusal-Vector Ablation to Llama 3.1 70B Agents
Simon Lermen, Mateusz Dziemian, Govind Pimpale
- Published: 12 Oct 2024, Last Modified: 14 Nov 2024
- SafeGenAi Poster
- Readers: Everyone
AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment
Pankayaraj Pathmanathan, Udari Madhushani Sehwag, Michael-Andrei Panaitescu-Liess, Furong Huang
- Published: 12 Oct 2024, Last Modified: 21 Nov 2024
- SafeGenAi Poster
- Readers: Everyone