Evading Data Contamination Detection for Language Models is (too) Easy
Authors: Jasper Dekoninck, Mark Niklas Müller, Maximilian Baader, Marc Fischer, Martin Vechev | Published: 2024-02-05 | Updated: 2024-02-12
データ汚染検出
Time Travel in LLMs: Tracing Data Contamination in Large Language Models
Authors: Shahriar Golchin, Mihai Surdeanu | Published: 2023-08-16 | Updated: 2024-02-21
On Practical Aspects of Aggregation Defenses against Data Poisoning Attacks
Authors: Wenxiao Wang, Soheil Feizi | Published: 2023-06-28
Protecting Federated Learning from Extreme Model Poisoning Attacks via Multidimensional Time Series Anomaly Detection
Authors: Edoardo Gabrielli, Dimitri Belli, Zoe Matrullo, Vittorio Miori, Gabriele Tolomei | Published: 2023-03-29 | Updated: 2024-12-02
Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attacks
Authors: Yiwei Lu, Gautam Kamath, Yaoliang Yu | Published: 2023-03-07 | Updated: 2023-06-06
Performance Weighting for Robust Federated Learning Against Corrupted Sources
Authors: Dimitris Stripelis, Marcin Abram, Jose Luis Ambite | Published: 2022-05-02
GFCL: A GRU-based Federated Continual Learning Framework against Data Poisoning Attacks in IoV
Authors: Anum Talpur, Mohan Gurusamy | Published: 2022-04-23 | Updated: 2022-09-12
An Equivalence Between Data Poisoning and Byzantine Gradient Attacks
Authors: Sadegh Farhadkhani, Rachid Guerraoui, Lê-Nguyên Hoang, Oscar Villemaud | Published: 2022-02-17 | Updated: 2022-07-20
Excess Capacity and Backdoor Poisoning
Authors: Naren Sarayu Manoj, Avrim Blum | Published: 2021-09-02 | Updated: 2021-11-03
Adversarial Attacks Against Deep Reinforcement Learning Framework in Internet of Vehicles
Authors: Anum Talpur, Mohan Gurusamy | Published: 2021-08-02 | Updated: 2021-09-16