SafeSpec: Fast and Safe LLM via Dynamic Reflective Sampling
Authors: Haotian Xu, Zeyang Zhang, Linbao Li, Huadi Zheng, Yu Li, Cheng Zhuo | Published: 2026-06-18
CodeSentinel: A Three-Layer Defense Against Indirect Prompt Injection in Code Contexts
Authors: Po-Han Cheng, Chia-Mu Yu, Ying-Dar Lin, Yu-Sung Wu, Wei-Bin Lee | Published: 2026-06-17
Generalised Eigenvalue Geometry of Semantic Adversarial Attacks
Authors: Martin Anthony, Kaveh Salehzadeh Nobari | Published: 2026-06-17
Beyond Safe Data: Pretraining-Stage Alignment with Regular Safety Reflection
Authors: Jinhan Li, Kexian Tang, Yihan Xu, Zhuorui Ye, Kaifeng Lyu | Published: 2026-06-17
OpenAnt: LLM-Powered Vulnerability Discovery Through Code Decomposition, Adversarial Verification, and Dynamic Testing
Authors: Nahum Korda, Gadi Evron | Published: 2026-06-17
Giskard : Byzantine Robust and Confidential Aggregation for Large-Scale Decentralized Learning
Authors: Ousmane Touat, César Sabater, Mohamed Maouche, Sonia Ben Mokhtar | Published: 2026-06-17
PYPILINE: Malicious PyPI Package Detection via Suspicious API Knowledge and Agent Workflow
Authors: Siyuan Pang, Zhengwei Jiang, Yepeng Yao, Zijing Fan, Haozhe Li, Baoxu Liu | Published: 2026-06-17
Lifecycle-Aware Dynamic Analysis for Secure ML Model Execution
Authors: Gabriele Digregorio, Marco Di Gennaro, Francesco Pastore, Stefano Zanero, Stefano Longari, Michele Carminati | Published: 2026-06-17
TRAP: Benchmark for Task-completion and Resistance to Active Privacy-extraction
Authors: Moon Ye-Bin, Nam Hyeon-Woo, Baek Seong-Eun, Yejin Yeo, Tae-Hyun Oh | Published: 2026-06-17
Image Prompt Reconstruction Attacks on Distributed MLLM Inference Frameworks
Authors: Xinjian Luo, Hongyan Chang, Jianxin Wei, Yuncheng Wu, Xiaofeng Gao, Meikang Qiu, Ting Yu, Xue Liu | Published: 2026-06-17