{"total":55,"rows":[{"id":"2311.12075","title":"BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning","created":"2023-11-20","cited_by_count":115,"area":"safety"},{"id":"2404.15381","title":"Advances and Open Challenges in Federated Foundation Models","created":"2024-04-23","cited_by_count":36,"area":null},{"id":"2403.16257","title":"Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning","created":"2024-03-24","cited_by_count":31,"area":"safety"},{"id":"2408.07728","title":"Moderator: Moderating Text-to-Image Diffusion Models through Fine-grained Context-based Policies","created":"2024-08-14","cited_by_count":15,"area":"diffusion"},{"id":"2312.08890","title":"Defenses in Adversarial Machine Learning: A Survey","created":"2023-12-13","cited_by_count":14,"area":null},{"id":"2502.18290","title":"Stealthy Backdoor Attack in Self-Supervised Learning Vision Encoders for Large Vision Language Models","created":"2025-02-25","cited_by_count":14,"area":"mllm"},{"id":"2403.17188","title":"LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning","created":"2024-03-25","cited_by_count":13,"area":null},{"id":"2412.20392","title":"Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning","created":"2024-12-29","cited_by_count":12,"area":"safety"},{"id":"2409.15968","title":"Adversarial Backdoor Defense in CLIP","created":"2024-09-24","cited_by_count":10,"area":"safety"},{"id":"2312.10467","title":"TrojFSP: Trojan Insertion in Few-shot Prompt Tuning","created":"2023-12-16","cited_by_count":9,"area":null},{"id":"2506.07524","title":"TAI3: Testing Agent Integrity in Interpreting User Intent","created":"2025-06-09","cited_by_count":9,"area":"agents"},{"id":"2406.03508","title":"Mutual Information Guided Backdoor Mitigation for Pre-trained Encoders","created":"2024-06-05","cited_by_count":8,"area":"safety"},{"id":"2310.00626","title":"GhostEncoder: Stealthy Backdoor Attacks with Dynamic Triggers to Pre-trained Encoders in Self-supervised Learning","created":"2023-10-01","cited_by_count":6,"area":"safety"},{"id":"2403.03846","title":"Can Distillation Mitigate Backdoor Attacks in Pre-trained Encoders?","created":"2024-03-06","cited_by_count":6,"area":"safety"},{"id":"2405.14672","title":"Invisible Backdoor Attack against Self-supervised Learning","created":"2024-05-23","cited_by_count":6,"area":null},{"id":"2409.19526","title":"Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats","created":"2024-09-29","cited_by_count":6,"area":"safety"},{"id":"2411.16154","title":"DeDe: Detecting Backdoor Samples for SSL Encoders via Decoders","created":"2024-11-25","cited_by_count":6,"area":"safety"},{"id":"2503.05445","title":"Are Your LLM-based Text-to-SQL Models Secure? Exploring SQL Injection via Backdoor Attacks","created":"2025-03-07","cited_by_count":6,"area":"safety"},{"id":"2503.16872","title":"Lie Detector: Unified Backdoor Detection via Cross-Examination Framework","created":"2025-03-21","cited_by_count":6,"area":null},{"id":"2508.14015","title":"Backdooring Self-Supervised Contrastive Learning by Noisy Alignment","created":"2025-08-19","cited_by_count":6,"area":null},{"id":"2405.15269","title":"Test-Time Multimodal Backdoor Detection by Contrastive Prompting","created":"2024-05-24","cited_by_count":5,"area":"safety"},{"id":"2509.24566","title":"TokenSwap: Backdoor Attack on the Compositional Understanding of Large Vision-Language Models","created":"2025-09-29","cited_by_count":5,"area":"mllm"},{"id":"2511.18921","title":"BackdoorVLM: A Benchmark for Backdoor Attacks and Defenses on Vision-Language Models","created":"2025-11-24","cited_by_count":5,"area":"mllm"},{"id":"2603.12989","title":"Test-Time Attention Purification for Backdoored Large Vision Language Models","created":"2026-03-13","cited_by_count":5,"area":"mllm"},{"id":"2509.16950","title":"Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving","created":"2025-09-21","cited_by_count":4,"area":"safety"},{"id":"2502.19047","title":"A Dual-Purpose Framework for Backdoor Defense and Backdoor Amplification in Diffusion Models","created":"2025-02-26","cited_by_count":3,"area":"diffusion"},{"id":"2504.11990","title":"Secure Transfer Learning: Training Clean Models Against Backdoor in (Both) Pre-trained Encoders and Downstream Datasets","created":"2025-04-16","cited_by_count":3,"area":"safety"},{"id":"2509.18717","title":"Pre-training CLIP against Data Poisoning with Optimal Transport-based Matching and Alignment","created":"2025-09-23","cited_by_count":3,"area":"safety"},{"id":"2405.13080","title":"EmInspector: Combating Backdoor Attacks in Federated Self-Supervised Learning Through Embedding Inspection","created":"2024-05-21","cited_by_count":2,"area":null},{"id":"2407.11372","title":"UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening","created":"2024-07-16","cited_by_count":2,"area":null},{"id":"2411.07691","title":"New Emerged Security and Privacy of Pre-trained Model: a Survey and Outlook","created":"2024-11-12","cited_by_count":2,"area":null},{"id":"2411.13981","title":"On the Fairness, Diversity and Reliability of Text-to-Image Generative Models","created":"2024-11-21","cited_by_count":2,"area":null},{"id":"2506.07467","title":"Circumventing Backdoor Space via Weight Symmetry","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2602.17168","title":"BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning","created":"2026-02-19","cited_by_count":2,"area":"safety"},{"id":"2407.04179","title":"Defense Against Syntactic Textual Backdoor Attacks with Token Substitution","created":"2024-07-04","cited_by_count":1,"area":"safety"},{"id":"2502.16167","title":"PersGuard: Preventing Malicious Personalization in Text-to-Image Diffusion Models via Model Backdoors","created":"2025-02-22","cited_by_count":1,"area":"diffusion"},{"id":"2503.09095","title":"Backdooring CLIP through Concept Confusion","created":"2025-03-12","cited_by_count":1,"area":"safety"},{"id":"2506.12411","title":"InverTune: Removing Backdoors from Multimodal Contrastive Learning Models via Trigger Inversion and Activation Tuning","created":"2025-06-14","cited_by_count":1,"area":"safety"},{"id":"2506.17350","title":"CUBA: Controlled Untargeted Backdoor Attack against Deep Neural Networks","created":"2025-06-20","cited_by_count":1,"area":null},{"id":"2508.08031","title":"IPBA: Imperceptible Perturbation Backdoor Attack in Federated Self-Supervised Learning","created":"2025-08-11","cited_by_count":1,"area":null},{"id":"2510.14845","title":"Backdoor Unlearning by Linear Task Decomposition","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2603.11664","title":"BackdoorIDS: Zero-shot Backdoor Detection for Pretrained Vision Encoder","created":"2026-03-12","cited_by_count":1,"area":"mllm"},{"id":"2311.09680","title":"Trustworthy Large Models in Vision: A Survey","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2501.04108","title":"TrojanDec: Data-free Detection of Trojan Inputs in Self-supervised Learning","created":"2025-01-07","cited_by_count":0,"area":null},{"id":"2503.20925","title":"Prototype Guided Backdoor Defense","created":"2025-03-26","cited_by_count":0,"area":null},{"id":"2512.00343","title":"Assimilation Matters: Model-level Backdoor Detection in Vision-Language Pretrained Models","created":"2025-11-29","cited_by_count":0,"area":"mllm"},{"id":"2603.17174","title":"Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning","created":"2026-03-17","cited_by_count":0,"area":"safety"},{"id":"2603.27522","title":"Hidden Ads: Behavior Triggered Semantic Backdoors for Advertisement Injection in Vision Language Models","created":"2026-03-29","cited_by_count":0,"area":"mllm"},{"id":"2604.09101","title":"CLIP-Inspector: Model-Level Backdoor Detection for Prompt-Tuned CLIP via OOD Trigger Inversion","created":"2026-04-10","cited_by_count":0,"area":"mllm"},{"id":"2604.22550","title":"ArmSSL: Adversarial Robust Black-Box Watermarking for Self-Supervised Learning Pre-trained Encoders","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2606.29451","title":"The Platonic Defense: Backdoor Defense for Self-Supervised Encoders in the Era of Large Scale Pre-training","created":"2026-06-28","cited_by_count":0,"area":"safety"},{"id":"2608.25851","title":"DEFUSE: Generalizable Backdoor Defense for Self-Supervised Encoders with Generative Priors","created":"2026-08-26","cited_by_count":0,"area":"diffusion"},{"id":"2608.26861","title":"FIDA: Feature Instability-Driven Attack on Self-Supervised Facial Representation","created":"2026-08-27","cited_by_count":0,"area":"safety"},{"id":"2609.15781","title":"When the World Lies: Backdoor Attacks on Latent World Models for Downstream Control","created":"2026-09-14","cited_by_count":0,"area":"wm"},{"id":"2609.31558","title":"Region-Level Black-Box Defense Against Stealthy Embedding-Space Backdoors in CLIP","created":"2026-09-25","cited_by_count":0,"area":"safety"}],"next_cursor":null}