攻撃手法

Hard-Label Cryptanalytic Extraction of Neural Network Models

Authors: Yi Chen, Xiaoyang Dong, Jian Guo, Yantian Shen, Anyu Wang, Xiaoyun Wang | Published: 2024-09-18
モデル抽出攻撃
攻撃手法
計算複雑性

Context-Aware Membership Inference Attacks against Pre-trained Large Language Models

Authors: Hongyan Chang, Ali Shahin Shamsabadi, Kleomenis Katevas, Hamed Haddadi, Reza Shokri | Published: 2024-09-11
LLMセキュリティ
メンバーシップ推論
攻撃手法

AdaPPA: Adaptive Position Pre-Fill Jailbreak Attack Approach Targeting LLMs

Authors: Lijia Lv, Weigang Zhang, Xuehai Tang, Jie Wen, Feng Liu, Jizhong Han, Songlin Hu | Published: 2024-09-11
LLMセキュリティ
プロンプトインジェクション
攻撃手法

On the Weaknesses of Backdoor-based Model Watermarking: An Information-theoretic Perspective

Authors: Aoting Hu, Yanzhi Chen, Renjie Xie, Adrian Weller | Published: 2024-09-10
ウォーターマーキング
攻撃手法
透かしの耐久性

Well, that escalated quickly: The Single-Turn Crescendo Attack (STCA)

Authors: Alan Aqrawi, Arian Abbasi | Published: 2024-09-04 | Updated: 2024-09-10
LLMセキュリティ
コンテンツモデレーション
攻撃手法

Membership Inference Attacks Against In-Context Learning

Authors: Rui Wen, Zheng Li, Michael Backes, Yang Zhang | Published: 2024-09-02
プロンプトインジェクション
メンバーシップ推論
攻撃手法

Unveiling the Vulnerability of Private Fine-Tuning in Split-Based Frameworks for Large Language Models: A Bidirectionally Enhanced Attack

Authors: Guanzhong Chen, Zhenghan Qin, Mingxin Yang, Yajie Zhou, Tao Fan, Tianyu Du, Zenglin Xu | Published: 2024-09-02 | Updated: 2024-09-04
LLMセキュリティ
プロンプトインジェクション
攻撃手法

Is Difficulty Calibration All We Need? Towards More Practical Membership Inference Attacks

Authors: Yu He, Boheng Li, Yao Wang, Mengda Yang, Juan Wang, Hongxin Hu, Xingyu Zhao | Published: 2024-08-31 | Updated: 2024-09-04
メンバーシップ推論
攻撃手法
難易度キャリブレーション

AI-Driven Intrusion Detection Systems (IDS) on the ROAD Dataset: A Comparative Analysis for Automotive Controller Area Network (CAN)

Authors: Lorenzo Guerra, Linhan Xu, Paolo Bellavista, Thomas Chapuis, Guillaume Duc, Pavlo Mozharovskyi, Van-Tam Nguyen | Published: 2024-08-30 | Updated: 2024-09-05
攻撃手法
自動化された侵入検知システム
車両ネットワークセキュリティ

LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet

Authors: Nathaniel Li, Ziwen Han, Ian Steneker, Willow Primack, Riley Goodside, Hugh Zhang, Zifan Wang, Cristina Menghini, Summer Yue | Published: 2024-08-27 | Updated: 2024-09-04
プロンプトインジェクション
ユーザー教育
攻撃手法