Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts
Authors: Chiyu Zhang, Lu Zhou, Xiaogang Xu, Jiafei Wu, Liming Fang, Zhe Liu | Published: 2025-08-14
Prompt Injection
Demystifying the Role of Rule-based Detection in AI Systems for Windows Malware Detection
Authors: Andrea Ponte, Luca Demetrio, Luca Oneto, Ivan Tesfai Ogbu, Battista Biggio, Fabio Roli | Published: 2025-08-13
Attacks and Defenses Against LLM Fingerprinting
Authors: Kevin Kurian, Ethan Holland, Sean Oesch | Published: 2025-08-12
Oblivionis: A Lightweight Learning and Unlearning Framework for Federated Large Language Models
Authors: Fuyao Zhang, Xinyu Yan, Tiantong Wu, Wenjie Li, Tianxiang Chen, Yang Cao, Ran Yan, Longtao Huang, Wei Yang Bryan Lim, Qiang Yang | Published: 2025-08-12
Robust Anomaly Detection in O-RAN: Leveraging LLMs against Data Manipulation Attacks
Authors: Thusitha Dayaratne, Ngoc Duy Pham, Viet Vo, Shangqi Lai, Sharif Abuadbba, Hajime Suzuki, Xingliang Yuan, Carsten Rudolph | Published: 2025-08-11
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
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
VFLAIR-LLM: A Comprehensive Framework and Benchmark for Split Learning of LLMs
Authors: Zixuan Gu, Qiufeng Fan, Long Sun, Yang Liu, Xiaojun Ye | Published: 2025-08-05
PhishParrot: LLM-Driven Adaptive Crawling to Unveil Cloaked Phishing Sites
Authors: Hiroki Nakano, Takashi Koide, Daiki Chiba | Published: 2025-08-04
Breaking Obfuscation: Cluster-Aware Graph with LLM-Aided Recovery for Malicious JavaScript Detection
Authors: Zhihong Liang, Xin Wang, Zhenhuang Hu, Liangliang Song, Lin Chen, Jingjing Guo, Yanbin Wang, Ye Tian | Published: 2025-07-30