攻撃の評価

Jailbreak Distillation: Renewable Safety Benchmarking

Authors: Jingyu Zhang, Ahmed Elgohary, Xiawei Wang, A S M Iftekhar, Ahmed Magooda, Benjamin Van Durme, Daniel Khashabi, Kyle Jackson | Published: 2025-05-28
プロンプトインジェクション
モデル評価
攻撃の評価

Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space

Authors: Yao Huang, Yitong Sun, Shouwei Ruan, Yichi Zhang, Yinpeng Dong, Xingxing Wei | Published: 2025-05-27
LLMの安全機構の解除
プロンプトインジェクション
攻撃の評価

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling

Authors: Yichuan Cao, Yibo Miao, Xiao-Shan Gao, Yinpeng Dong | Published: 2025-05-27
モデル評価
実験的検証
攻撃の評価

Beyond Surface-Level Patterns: An Essence-Driven Defense Framework Against Jailbreak Attacks in LLMs

Authors: Shiyu Xiang, Ansen Zhang, Yanfei Cao, Yang Fan, Ronghao Chen | Published: 2025-02-26 | Updated: 2025-05-28
LLMセキュリティ
プロンプトインジェクション
攻撃の評価

Computing Optimization-Based Prompt Injections Against Closed-Weights Models By Misusing a Fine-Tuning API

Authors: Andrey Labunets, Nishit V. Pandya, Ashish Hooda, Xiaohan Fu, Earlence Fernandes | Published: 2025-01-16
プロンプトインジェクション
攻撃の評価
最適化問題

Neural Honeytrace: A Robust Plug-and-Play Watermarking Framework against Model Extraction Attacks

Authors: Yixiao Xu, Binxing Fang, Rui Wang, Yinghai Zhou, Shouling Ji, Yuan Liu, Mohan Li, Zhihong Tian | Published: 2025-01-16 | Updated: 2025-01-17
ウォーターマーキング
モデル抽出攻撃
攻撃の評価

Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards

Authors: Yangsibo Huang, Milad Nasr, Anastasios Angelopoulos, Nicholas Carlini, Wei-Lin Chiang, Christopher A. Choquette-Choo, Daphne Ippolito, Matthew Jagielski, Katherine Lee, Ken Ziyu Liu, Ion Stoica, Florian Tramer, Chiyuan Zhang | Published: 2025-01-13
サイバーセキュリティ
大規模言語モデル
攻撃の評価

Learning-based Detection of GPS Spoofing Attack for Quadrotors

Authors: Pengyu Wang, Zhaohua Yang, Jialu Li, Ling Shi | Published: 2025-01-10
サイバーセキュリティ
実験的検証
攻撃の評価

Image-based Multimodal Models as Intruders: Transferable Multimodal Attacks on Video-based MLLMs

Authors: Linhao Huang, Xue Jiang, Zhiqiang Wang, Wentao Mo, Xi Xiao, Bo Han, Yongjie Yin, Feng Zheng | Published: 2025-01-02 | Updated: 2025-01-10
攻撃の評価
攻撃手法
敵対的サンプル

FEDLAD: Federated Evaluation of Deep Leakage Attacks and Defenses

Authors: Isaac Baglin, Xiatian Zhu, Simon Hadfield | Published: 2024-11-05 | Updated: 2025-01-05
ポイズニング
攻撃の評価
評価手法