Showing 1–20 of 36 results
/ Date/ Name
Feb 7, 2023SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction ConsistencyMar 24, 2020PoisHygiene: Detecting and Mitigating Poisoning Attacks in Neural NetworksFeb 8, 2022PolicyCleanse: Backdoor Detection and Mitigation in Reinforcement LearningFeb 4, 2021PredCoin: Defense against Query-based Hard-label AttackOct 28, 2021AEVA: Black-box Backdoor Detection Using Adversarial Extreme Value AnalysisJul 10, 2020LINTS^RT: A Learning-driven Testbed for Intelligent Scheduling in Embedded SystemsJul 9, 2019PhysGAN: Generating Physical-World-Resilient Adversarial Examples for Autonomous DrivingOct 9, 2023Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at HandFeb 19, 2024Your Vision-Language Model Itself Is a Strong Filter: Towards High-Quality Instruction Tuning with Data SelectionDec 3, 2023Towards Sample-specific Backdoor Attack with Clean Labels via Attribute TriggerFeb 10, 2025Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models via ReasoningMay 20, 2025Modality-Balancing Preference Optimization of Large Multimodal Models by Adversarial Negative MiningApr 23, 2021Neural Mean Discrepancy for Efficient Out-of-Distribution DetectionOct 17, 2024A Watermark for Order-Agnostic Language ModelsOct 23, 2024Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model EditingNov 6, 2016Energy-Efficient Resource Allocation for Multi-User Mobile Edge ComputingMay 19, 2025Web Intellectual Property at Risk: Preventing Unauthorized Real-Time Retrieval by Large Language ModelsOct 17, 2024De-mark: Watermark Removal in Large Language ModelsDec 6, 2024SleeperMark: Towards Robust Watermark against Fine-Tuning Text-to-image Diffusion ModelsSep 13, 2023MASTERKEY: Practical Backdoor Attack Against Speaker Verification Systems