Understanding LLM Behavior When Encountering User-Supplied Harmful Content in Harmless Tasks
Authors: Junjie Chu, Yiting Qu, Ye Leng, Michael Backes, Yun Shen, Savvas Zannettou, Yang Zhang | Published: 2026-03-12
Prompt leaking
CacheSolidarity: Preventing Prefix Caching Side Channels in Multi-tenant LLM Serving Systems
Authors: Panagiotis Georgios Pennas, Konstantinos Papaioannou, Marco Guarnieri, Thaleia Dimitra Doudali | Published: 2026-03-11
Measuring Privacy vs. Fidelity in Synthetic Social Media Datasets
Authors: Henry Tari, Adriana Iamnitchi | Published: 2026-03-04
Inference-Time Safety For Code LLMs Via Retrieval-Augmented Revision
Authors: Manisha Mukherjee, Vincent J. Hellendoorn | Published: 2026-03-02
Assessing Deanonymization Risks with Stylometry-Assisted LLM Agent
Authors: Boyang Zhang, Yang Zhang | Published: 2026-02-26
Red-Teaming Claude Opus and ChatGPT-based Security Advisors for Trusted Execution Environments
Authors: Kunal Mukherjee | Published: 2026-02-23
Differentially Private and Communication Efficient Large Language Model Split Inference via Stochastic Quantization and Soft Prompt
Authors: Yujie Gu, Richeng Jin, Xiaoyu Ji, Yier Jin, Wenyuan Xu | Published: 2026-02-12
Focus Session: LLM4PQC — An Agentic Framework for Accurate and Efficient Synthesis of PQC Cores
Authors: Buddhi Perera, Zeng Wang, Weihua Xiao, Mohammed Nabeel, Ozgur Sinanoglu, Johann Knechtel, Ramesh Karri | Published: 2026-02-10
LogicScan: An LLM-driven Framework for Detecting Business Logic Vulnerabilities in Smart Contracts
Authors: Jiaqi Gao, Zijian Zhang, Yuqiang Sun, Ye Liu, Chengwei Liu, Han Liu, Yi Li, Yang Liu | Published: 2026-02-03
ICL-EVADER: Zero-Query Black-Box Evasion Attacks on In-Context Learning and Their Defenses
Authors: Ningyuan He, Ronghong Huang, Qianqian Tang, Hongyu Wang, Xianghang Mi, Shanqing Guo | Published: 2026-01-29