Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning
Authors: Shuai Zhao, Meihuizi Jia, Luu Anh Tuan, Fengjun Pan, Jinming Wen | Published: 2024-01-11 | Updated: 2024-10-09
バックドア攻撃
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
Authors: Evan Hubinger, Carson Denison, Jesse Mu, Mike Lambert, Meg Tong, Monte MacDiarmid, Tamera Lanham, Daniel M. Ziegler, Tim Maxwell, Newton Cheng, Adam Jermyn, Amanda Askell, Ansh Radhakrishnan, Cem Anil, David Duvenaud, Deep Ganguli, Fazl Barez, Jack Clark, Kamal Ndousse, Kshitij Sachan, Michael Sellitto, Mrinank Sharma, Nova DasSarma, Roger Grosse, Shauna Kravec, Yuntao Bai, Zachary Witten, Marina Favaro, Jan Brauner, Holden Karnofsky, Paul Christiano, Samuel R. Bowman, Logan Graham, Jared Kaplan, Sören Mindermann, Ryan Greenblatt, Buck Shlegeris, Nicholas Schiefer, Ethan Perez | Published: 2024-01-10 | Updated: 2024-01-17
MalModel: Hiding Malicious Payload in Mobile Deep Learning Models with Black-box Backdoor Attack
Authors: Jiayi Hua, Kailong Wang, Meizhen Wang, Guangdong Bai, Xiapu Luo, Haoyu Wang | Published: 2024-01-05
FedBayes: A Zero-Trust Federated Learning Aggregation to Defend Against Adversarial Attacks
Authors: Marc Vucovich, Devin Quinn, Kevin Choi, Christopher Redino, Abdul Rahman, Edward Bowen | Published: 2023-12-04
Understanding Variation in Subpopulation Susceptibility to Poisoning Attacks
Authors: Evan Rose, Fnu Suya, David Evans | Published: 2023-11-20
TextGuard: Provable Defense against Backdoor Attacks on Text Classification
Authors: Hengzhi Pei, Jinyuan Jia, Wenbo Guo, Bo Li, Dawn Song | Published: 2023-11-19 | Updated: 2023-11-25
Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections
Authors: Yuanpu Cao, Bochuan Cao, Jinghui Chen | Published: 2023-11-15 | Updated: 2024-06-09
Label Poisoning is All You Need
Authors: Rishi D. Jha, Jonathan Hayase, Sewoong Oh | Published: 2023-10-29
On the Detection of Image-Scaling Attacks in Machine Learning
Authors: Erwin Quiring, Andreas Müller, Konrad Rieck | Published: 2023-10-23
FLEDGE: Ledger-based Federated Learning Resilient to Inference and Backdoor Attacks
Authors: Jorge Castillo, Phillip Rieger, Hossein Fereidooni, Qian Chen, Ahmad Sadeghi | Published: 2023-10-03