NeurIPS 2023 Workshop BUGS Submissions

Clean-label Backdoor Attacks by Selectively Poisoning with Limited Information from Target Class
Nguyen Hung-Quang, Ngoc-Hieu Nguyen, The-Anh Ta, Thanh Nguyen-Tang, Hoang Thanh-Tung, Khoa D Doan
- Published: 28 Oct 2023, Last Modified: 13 Mar 2024
- NeurIPS 2023 BUGS Poster
- Readers: Everyone
Universal Trojan Signatures in Reinforcement Learning
Manoj Acharya, Weichao Zhou, Anirban Roy, Xiao Lin, Wenchao Li, Susmit Jha
- Published: 28 Oct 2023, Last Modified: 13 Mar 2024
- NeurIPS 2023 BUGS Poster
- Readers: Everyone
Analyzing And Editing Inner Mechanisms of Backdoored Language Models
Max Lamparth, Ann-Katrin Reuel
- Published: 28 Oct 2023, Last Modified: 13 Mar 2024
- NeurIPS 2023 BUGS Poster
- Readers: Everyone
Forcing Generative Models to Degenerate Ones: The Power of Data Poisoning Attacks
Shuli Jiang, Swanand Kadhe, Yi Zhou, Ling Cai, Nathalie Baracaldo
- Published: 28 Oct 2023, Last Modified: 13 Mar 2024
- NeurIPS 2023 BUGS Poster
- Readers: Everyone
BadFusion: 2D-Oriented Backdoor Attacks against 3D Object Detection
Saket Sanjeev Chaturvedi, Lan Zhang, Wenbin Zhang, Pan He, Xiaoyong Yuan
- Published: 28 Oct 2023, Last Modified: 13 Mar 2024
- NeurIPS 2023 BUGS Poster
- Readers: Everyone
Effective Backdoor Mitigation Depends on the Pre-training Objective
Sahil Verma, Gantavya Bhatt, Soumye Singhal, Arnav Mohanty Das, Chirag Shah, John P Dickerson, Jeff Bilmes
- Published: 28 Oct 2023, Last Modified: 13 Mar 2024
- NeurIPS 2023 BUGS Oral
- Readers: Everyone
Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection
Jun Yan, Vikas Yadav, Shiyang Li, Lichang Chen, Zheng Tang, Hai Wang, Vijay Srinivasan, Xiang Ren, Hongxia Jin
- Published: 28 Oct 2023, Last Modified: 13 Mar 2024
- NeurIPS 2023 BUGS Oral
- Readers: Everyone
Benchmark Probing: Investigating Data Leakage in Large Language Models
Chunyuan Deng, Yilun Zhao, Xiangru Tang, Mark Gerstein, Arman Cohan
- Published: 28 Oct 2023, Last Modified: 13 Mar 2024
- NeurIPS 2023 BUGS Poster
- Readers: Everyone
From Trojan Horses to Castle Walls: Unveiling Bilateral Backdoor Effects in Diffusion Models
Zhuoshi Pan, Yuguang Yao, Gaowen Liu, Bingquan Shen, H. Vicky Zhao, Ramana Rao Kompella, Sijia Liu
- Published: 28 Oct 2023, Last Modified: 13 Mar 2024
- NeurIPS 2023 BUGS Poster
- Readers: Everyone
Adversarial Robustness Unhardening via Backdoor Attacks in Federated Learning
Taejin Kim, Jiarui Li, Nikhil Madaan, Shubhranshu Singh, Carlee Joe-Wong
- Published: 28 Oct 2023, Last Modified: 13 Mar 2024
- NeurIPS 2023 BUGS Poster
- Readers: Everyone
BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models
Zhen Xiang, Fengqing Jiang, Zidi Xiong, Bhaskar Ramasubramanian, Radha Poovendran, Bo Li
- Published: 28 Oct 2023, Last Modified: 13 Mar 2024
- NeurIPS 2023 BUGS Oral
- Readers: Everyone
The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright Breaches Without Adjusting Finetuning Pipeline
Haonan Wang, Qianli Shen, Yao Tong, Yang Zhang, Kenji Kawaguchi
- Published: 28 Oct 2023, Last Modified: 13 Mar 2024
- NeurIPS 2023 BUGS Oral
- Readers: Everyone
$D^3$: Detoxing Deep Learning Dataset
Lu Yan, Siyuan Cheng, Guangyu Shen, Guanhong Tao, Xuan Chen, Kaiyuan Zhang, Yunshu Mao, Xiangyu Zhang
- Published: 28 Oct 2023, Last Modified: 13 Mar 2024
- NeurIPS 2023 BUGS Poster
- Readers: Everyone
On the Limitation of Backdoor Detection Methods
Georg Pichler, Marco Romanelli, Divya Prakash Manivannan, Prashanth Krishnamurthy, Farshad Khorrami, Siddharth Garg
- Published: 28 Oct 2023, Last Modified: 13 Mar 2024
- NeurIPS 2023 BUGS Poster
- Readers: Everyone
Detecting Backdoors with Meta-Models
Lauro Langosco, Neel Alex, William Baker, David Quarel, Herbie Bradley, David Krueger
- Published: 28 Oct 2023, Last Modified: 13 Mar 2024
- NeurIPS 2023 BUGS Poster
- Readers: Everyone
How to remove backdoors in diffusion models?
Shengwei An, Sheng-Yen Chou, Kaiyuan Zhang, Qiuling Xu, Guanhong Tao, Guangyu Shen, Siyuan Cheng, Shiqing Ma, Pin-Yu Chen, Tsung-Yi Ho, Xiangyu Zhang
- Published: 28 Oct 2023, Last Modified: 13 Mar 2024
- NeurIPS 2023 BUGS Poster
- Readers: Everyone
Defending Our Privacy With Backdoors
Dominik Hintersdorf, Lukas Struppek, Daniel Neider, Kristian Kersting
- Published: 28 Oct 2023, Last Modified: 13 Mar 2024
- NeurIPS 2023 BUGS Poster
- Readers: Everyone
VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models
Sheng-Yen Chou, Pin-Yu Chen, Tsung-Yi Ho
- Published: 28 Oct 2023, Last Modified: 13 Mar 2024
- NeurIPS 2023 BUGS Oral
- Readers: Everyone
Leveraging Diffusion-Based Image Variations for Robust Training on Poisoned Data
Lukas Struppek, Martin Hentschel, Clifton Poth, Dominik Hintersdorf, Kristian Kersting
- Published: 28 Oct 2023, Last Modified: 13 Mar 2024
- NeurIPS 2023 BUGS Poster
- Readers: Everyone
How to Backdoor HyperNetwork in Personalized Federated Learning?
Phung Lai, Hai Phan, Issa Khalil, Abdallah Khreishah, Xintao Wu
- Published: 28 Oct 2023, Last Modified: 13 Mar 2024
- NeurIPS 2023 BUGS Poster
- Readers: Everyone