model security

Defending against Backdoor Attacks in Natural Language Generation AAAI 2023 Django: Detecting Trojans in Object Detection Models via Gaussian Focus Calibration NeurIPS 2023 Effective Ambiguity Attack Against Passport-Based DNN Intellectual Property Protection Schemes Through Fully Connected Layer Substitution CVPR 2023 IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks ACL 2023 Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features NeurIPS 2023 NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models ACL 2023 One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training ICCV 2023 Preprocessors Matter! Realistic Decision-Based Attacks on Machine Learning Systems ICML 2023 Revisiting Data-Free Knowledge Distillation with Poisoned Teachers ICML 2023 Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis ICCV 2023 Scalable Membership Inference Attacks via Quantile Regression NeurIPS 2023 TrojanSQL: SQL Injection against Natural Language Interface to Database EMNLP 2023 TrojDiff: Trojan Attacks on Diffusion Models With Diverse Targets CVPR 2023 TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models NeurIPS 2023 Understanding Backdoor Attacks through the Adaptability Hypothesis ICML 2023 UPTON: Preventing Authorship Leakage from Public Text Release via Data Poisoning EMNLP 2023 XRand: Differentially Private Defense against Explanation-Guided Attacks AAAI 2023 A Study of the Attention Abnormality in Trojaned BERTs NAACL 2022 A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks NeurIPS 2022 Autoregressive Perturbations for Data Poisoning NeurIPS 2022 Better Trigger Inversion Optimization in Backdoor Scanning CVPR 2022 Defending against Model Stealing via Verifying Embedded External Features AAAI 2022 Effective Backdoor Defense by Exploiting Sensitivity of Poisoned Samples NeurIPS 2022 Imperceptible Backdoor Attack: From Input Space to Feature Representation IJCAI 2022 Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class NeurIPS 2022