Generative Large Language Model usage in Smart Contract Vulnerability Detection
Authors: Peter Ince, Jiangshan Yu, Joseph K. Liu, Xiaoning Du | Published: 2025-04-07
AIセキュリティポータルbot
TrafficLLM: Enhancing Large Language Models for Network Traffic Analysis with Generic Traffic Representation
Authors: Tianyu Cui, Xinjie Lin, Sijia Li, Miao Chen, Qilei Yin, Qi Li, Ke Xu | Published: 2025-04-05 | Updated: 2025-04-15
Les Dissonances: Cross-Tool Harvesting and Polluting in Multi-Tool Empowered LLM Agents
Authors: Zichuan Li, Jian Cui, Xiaojing Liao, Luyi Xing | Published: 2025-04-04 | Updated: 2025-04-28
Accelerating IoV Intrusion Detection: Benchmarking GPU-Accelerated vs CPU-Based ML Libraries
Authors: Furkan Çolhak, Hasan Coşkun, Tsafac Nkombong Regine Cyrille, Tedi Hoxa, Mert İlhan Ecevit, Mehmet Nafiz Aydın | Published: 2025-04-02 | Updated: 2025-04-03
Representation Bending for Large Language Model Safety
Authors: Ashkan Yousefpour, Taeheon Kim, Ryan S. Kwon, Seungbeen Lee, Wonje Jeung, Seungju Han, Alvin Wan, Harrison Ngan, Youngjae Yu, Jonghyun Choi | Published: 2025-04-02
LightDefense: A Lightweight Uncertainty-Driven Defense against Jailbreaks via Shifted Token Distribution
Authors: Zhuoran Yang, Jie Peng, Zhen Tan, Tianlong Chen, Yanyong Zhang | Published: 2025-04-02
Identifying Obfuscated Code through Graph-Based Semantic Analysis of Binary Code
Authors: Roxane Cohen, Robin David, Florian Yger, Fabrice Rossi | Published: 2025-04-02
PiCo: Jailbreaking Multimodal Large Language Models via $\textbf{Pi}$ctorial $\textbf{Co}$de Contextualization
Authors: Aofan Liu, Lulu Tang, Ting Pan, Yuguo Yin, Bin Wang, Ao Yang | Published: 2025-04-02 | Updated: 2025-04-07
On Benchmarking Code LLMs for Android Malware Analysis
Authors: Yiling He, Hongyu She, Xingzhi Qian, Xinran Zheng, Zhuo Chen, Zhan Qin, Lorenzo Cavallaro | Published: 2025-04-01 | Updated: 2025-04-23
No Free Lunch with Guardrails
Authors: Divyanshu Kumar, Nitin Aravind Birur, Tanay Baswa, Sahil Agarwal, Prashanth Harshangi | Published: 2025-04-01 | Updated: 2025-04-03