Revisiting Character-level Adversarial Attacks for Language Models
Authors: Elias Abad Rocamora, Yongtao Wu, Fanghui Liu, Grigorios G. Chrysos, Volkan Cevher | Published: 2024-05-07 | Updated: 2024-09-04
攻撃手法
Boosting Jailbreak Attack with Momentum
Authors: Yihao Zhang, Zeming Wei | Published: 2024-05-02
Attacks on Third-Party APIs of Large Language Models
Authors: Wanru Zhao, Vidit Khazanchi, Haodi Xing, Xuanli He, Qiongkai Xu, Nicholas Donald Lane | Published: 2024-04-24
MISLEAD: Manipulating Importance of Selected features for Learning Epsilon in Evasion Attack Deception
Authors: Vidit Khazanchi, Pavan Kulkarni, Yuvaraj Govindarajulu, Manojkumar Parmar | Published: 2024-04-24 | Updated: 2024-05-02
Black-box Adversarial Transferability: An Empirical Study in Cybersecurity Perspective
Authors: Khushnaseeb Roshan, Aasim Zafar | Published: 2024-04-15
Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs
Authors: Bibek Upadhayay, Vahid Behzadan | Published: 2024-04-09
Aggressive or Imperceptible, or Both: Network Pruning Assisted Hybrid Byzantines in Federated Learning
Authors: Emre Ozfatura, Kerem Ozfatura, Alptekin Kupcu, Deniz Gunduz | Published: 2024-04-09
BruSLeAttack: A Query-Efficient Score-Based Black-Box Sparse Adversarial Attack
Authors: Viet Quoc Vo, Ehsan Abbasnejad, Damith C. Ranasinghe | Published: 2024-04-08 | Updated: 2024-06-01
Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
Authors: Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion | Published: 2024-04-02 | Updated: 2024-10-07
Humanizing Machine-Generated Content: Evading AI-Text Detection through Adversarial Attack
Authors: Ying Zhou, Ben He, Le Sun | Published: 2024-04-02