文献データベース

JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering

Authors: Renmiao Chen, Shiyao Cui, Xuancheng Huang, Chengwei Pan, Victor Shea-Jay Huang, QingLin Zhang, Xuan Ouyang, Zhexin Zhang, Hongning Wang, Minlie Huang | Published: 2025-08-07
プロンプトインジェクション
不適切コンテンツ生成
攻撃戦略分析

Measuring the Carbon Footprint of Cryptographic Privacy-Enhancing Technologies

Authors: Marc Damie, Mihai Pop, Merijn Posthuma | Published: 2025-08-06
カーボンフットプリント分析
環境影響評価
通信セキュリティ

Matrix-Free Two-to-Infinity and One-to-Two Norms Estimation

Authors: Askar Tsyganov, Evgeny Frolov, Sergey Samsonov, Maxim Rakhuba | Published: 2025-08-06
ロバスト最適化
性能評価手法
深層学習

Prompt Injection Vulnerability of Consensus Generating Applications in Digital Democracy

Authors: Jairo Gudiño-Rosero, Clément Contet, Umberto Grandi, César A. Hidalgo | Published: 2025-08-06
インダイレクトプロンプトインジェクション
倫理的考慮
公平性の確保

Leveraging large language models for SQL behavior-based database intrusion detection

Authors: Meital Shlezinger, Shay Akirav, Lei Zhou, Liang Guo, Avi Kessel, Guoliang Li | Published: 2025-08-06 | Updated: 2025-08-14
アンサンブル学習
データ前処理
ユーザー行動分析

What If, But Privately: Private Counterfactual Retrieval

Authors: Shreya Meel, Mohamed Nomeir, Pasan Dissanayake, Sanghamitra Dutta, Sennur Ulukus | Published: 2025-08-05
プライバシー保護手法
計算複雑性
通信セキュリティ

Intrusion Detection in Heterogeneous Networks with Domain-Adaptive Multi-Modal Learning

Authors: Mabin Umman Varghese, Zahra Taghiyarrenani | Published: 2025-08-05
データセットの多様性
敵対的学習
深層学習モデル

When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs

Authors: Bodam Kim, Hiskias Dingeto, Taeyoun Kwon, Dasol Choi, DongGeon Lee, Haon Park, JaeHoon Lee, Jongho Shin | Published: 2025-08-05
プロンプトインジェクション
攻撃の評価
音声モデルの脆弱性

From Legacy to Standard: LLM-Assisted Transformation of Cybersecurity Playbooks into CACAO Format

Authors: Mehdi Akbari Gurabi, Lasse Nitz, Radu-Mihai Castravet, Roman Matzutt, Avikarsha Mandal, Stefan Decker | Published: 2025-08-05
セキュリティ分析
テキスト生成手法
モデル抽出攻撃

Attack the Messages, Not the Agents: A Multi-round Adaptive Stealthy Tampering Framework for LLM-MAS

Authors: Bingyu Yan, Ziyi Zhou, Xiaoming Zhang, Chaozhuo Li, Ruilin Zeng, Yirui Qi, Tianbo Wang, Litian Zhang | Published: 2025-08-05
強化学習攻撃
攻撃アクションモデル
透かし