Showing 1–15 of 15 results
/ Date/ Name
Oct 19, 2023Formalizing and Benchmarking Prompt Injection Attacks and DefensesMar 26, 2023PORE: Provably Robust Recommender Systems against Data Poisoning AttacksJan 7, 2025TrojanDec: Data-free Detection of Trojan Inputs in Self-supervised LearningSep 29, 2025SecInfer: Preventing Prompt Injection via Inference-time ScalingApr 15, 2025DataSentinel: A Game-Theoretic Detection of Prompt Injection AttacksAug 14, 2024Evaluating LLM-based Personal Information Extraction and CountermeasuresAug 1, 2021BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised LearningDec 7, 2020Certified Robustness of Nearest Neighbors against Data Poisoning and Backdoor AttacksFeb 27, 2025SecureGaze: Defending Gaze Estimation Against Backdoor AttacksJun 13, 2021Security Analysis of Camera-LiDAR Fusion Against Black-Box Attacks on Autonomous VehiclesJan 15, 2022StolenEncoder: Stealing Pre-trained Encoders in Self-supervised LearningNov 7, 2024Defending Deep Regression Models against Backdoor AttacksOct 14, 2025PromptLocate: Localizing Prompt Injection AttacksMay 23, 2025A Critical Evaluation of Defenses against Prompt Injection AttacksOct 15, 2025PIShield: Detecting Prompt Injection Attacks via Intrinsic LLM Features