backdoor detection

An LLM-based Quantitative Framework for Evaluating High-Stealthy Backdoor Risks in OSS Supply Chains AAAI 2026 ConfGuard: A Simple and Effective Backdoor Detection for Large Language Models AAAI 2026 DUP: Detection-guided Unlearning for Backdoor Purification in Language Models AAAI 2026 Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models UAI 2026 Probing Semantic Insensitivity for Inference-Time Backdoor Defense in Multimodal Large Language Model AAAI 2026 Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats ICLR 2025 DeDe: Detecting Backdoor Samples for SSL Encoders via Decoders CVPR 2025 Detecting Backdoor Samples in Contrastive Language Image Pretraining ICLR 2025 Detecting Stealthy Backdoor Samples based on Intra-class Distance for Large Language Models EMNLP 2025 PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection CVPR 2025 Rethinking Backdoor Detection Evaluation for Language Models EMNLP 2025 Tell me about yourself: LLMs are aware of their learned behaviors ICLR 2025 Test-Time Backdoor Detection for Object Detection Models CVPR 2025 Test-Time Multimodal Backdoor Detection by Contrastive Prompting ICML 2025 UFID: A Unified Framework for Black-box Input-level Backdoor Detection on Diffusion Models AAAI 2025 Attack To Defend: Exploiting Adversarial Attacks for Detecting Poisoned Models CVPR 2024 Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency ICLR 2024 BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection ICLR 2024 BAN: Detecting Backdoors Activated by Adversarial Neuron Noise NeurIPS 2024 Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift AAAI 2024 Energy-based Backdoor Defense without Task-Specific Samples and Model Retraining ICML 2024 LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning CVPR 2024 On the (In)feasibility of ML Backdoor Detection as an Hypothesis Testing Problem AISTATS 2024 Scanning Trojaned Models Using Out-of-Distribution Samples NeurIPS 2024 SEER: Backdoor Detection for Vision-Language Models through Searching Target Text and Image Trigger Jointly AAAI 2024