{"total":63,"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":"2402.13851","title":"VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models","created":"2024-02-21","cited_by_count":87,"area":"mllm"},{"id":"2407.07403","title":"A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends","created":"2024-07-10","cited_by_count":84,"area":"mllm"},{"id":"2311.16194","title":"BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP","created":"2023-11-26","cited_by_count":67,"area":"mllm"},{"id":"2305.06360","title":"Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy","created":"2023-05-10","cited_by_count":51,"area":"safety"},{"id":"2402.08577","title":"Test-Time Backdoor Attacks on Multimodal Large Language Models","created":"2024-02-13","cited_by_count":40,"area":"mllm"},{"id":"2403.13682","title":"Threats, Attacks, and Defenses in Machine Unlearning: A Survey","created":"2024-03-20","cited_by_count":39,"area":"safety"},{"id":"2303.06854","title":"Robust Contrastive Language-Image Pre-training against Data Poisoning and Backdoor Attacks","created":"2023-03-13","cited_by_count":31,"area":"mllm"},{"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":"2405.16134","title":"Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack","created":"2024-05-25","cited_by_count":28,"area":null},{"id":"2502.17832","title":"MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks","created":"2025-02-25","cited_by_count":24,"area":"mllm"},{"id":"2310.05862","title":"Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks","created":"2023-10-05","cited_by_count":19,"area":"safety"},{"id":"2312.08890","title":"Defenses in Adversarial Machine Learning: A Survey","created":"2023-12-13","cited_by_count":14,"area":null},{"id":"2309.10283","title":"FRAMU: Attention-based Machine Unlearning using Federated Reinforcement Learning","created":"2023-09-19","cited_by_count":13,"area":"safety"},{"id":"2307.12980","title":"A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models","created":"2023-07-24","cited_by_count":12,"area":"mllm"},{"id":"2407.14971","title":"Sim-CLIP: Unsupervised Siamese Adversarial Fine-Tuning for Robust and Semantically-Rich Vision-Language Models","created":"2024-07-20","cited_by_count":12,"area":"mllm"},{"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":"2411.15673","title":"Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment","created":"2024-11-23","cited_by_count":7,"area":"mllm"},{"id":"2607.07907","title":"Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks","created":"2026-07-08","cited_by_count":7,"area":"safety"},{"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":"2503.18695","title":"OCRT: Boosting Foundation Models in the Open World with Object-Concept-Relation Triad","created":"2025-03-24","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":"2405.16783","title":"TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models","created":"2024-05-27","cited_by_count":5,"area":"safety"},{"id":"2501.13340","title":"Retrievals Can Be Detrimental: Unveiling the Backdoor Vulnerability of Retrieval-Augmented Diffusion Models","created":"2025-01-23","cited_by_count":5,"area":"rag"},{"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":"2409.16057","title":"Towards Robust Object Detection: Identifying and Removing Backdoors via Module Inconsistency Analysis","created":"2024-09-24","cited_by_count":4,"area":null},{"id":"2412.00727","title":"Perturb and Recover: Fine-tuning for Effective Backdoor Removal from CLIP","created":"2024-12-01","cited_by_count":4,"area":"mllm"},{"id":"2511.00446","title":"ToxicTextCLIP: Text-Based Poisoning and Backdoor Attacks on CLIP Pre-training","created":"2025-11-01","cited_by_count":4,"area":"mllm"},{"id":"2501.02373","title":"BADTV: Unveiling Backdoor Threats in Third-Party Task Vectors","created":"2025-01-04","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":"2510.19384","title":"Learning Noise-Resilient and Transferable Graph-Text Alignment via Dynamic Quality Assessment","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2311.14948","title":"Effective Backdoor Mitigation in Vision-Language Models Depends on the Pre-training Objective","created":"2023-11-25","cited_by_count":2,"area":"mllm"},{"id":"2312.07955","title":"Erasing Self-Supervised Learning Backdoor by Cluster Activation Masking","created":"2023-12-13","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":"2602.17168","title":"BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning","created":"2026-02-19","cited_by_count":2,"area":"safety"},{"id":"2306.02064","title":"Unlearnable Examples Give a False Sense of Data Privacy: Understanding and Relearning","created":"2023-06-03","cited_by_count":1,"area":null},{"id":"2401.15817","title":"Transparency Attacks: How Imperceptible Image Layers Can Fool AI Perception","created":"2024-01-29","cited_by_count":1,"area":"safety"},{"id":"2502.19269","title":"Neural Antidote: Class-Wise Prompt Tuning for Purifying Backdoors in CLIP","created":"2025-02-26","cited_by_count":1,"area":"mllm"},{"id":"2509.03433","title":"Decoding Visual Neural Representations by Multimodal with Dynamic Balancing","created":"2025-09-03","cited_by_count":1,"area":null},{"id":"2509.16060","title":"SABER: Uncovering Vulnerabilities in Safety Alignment via Cross-Layer Residual Connection","created":"2025-09-19","cited_by_count":1,"area":"alignment"},{"id":"2510.14845","title":"Backdoor Unlearning by Linear Task Decomposition","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2511.00523","title":"SegDebias: Test-Time Bias Mitigation for ViT-Based CLIP via Segmentation","created":"2025-11-01","cited_by_count":1,"area":"mllm"},{"id":"2511.14106","title":"Stealth Fine-Tuning: Efficiently Breaking Alignment in RVLMs Using Self-Generated CoT","created":"2025-11-18","cited_by_count":1,"area":"lr"},{"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":"2402.09671","title":"Exploiting Alpha Transparency In Language And Vision-Based AI Systems","created":"2024-02-15","cited_by_count":0,"area":null},{"id":"2508.08040","title":"BadPromptFL: A Novel Backdoor Threat to Prompt-based Federated Learning in Multimodal Models","created":"2025-08-11","cited_by_count":0,"area":"mllm"},{"id":"2508.13072","title":"A Language-Signal-Vision Multimodal Framework for Multitask Cardiac Analysis","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2511.12735","title":"Backdoor Attacks on Open Vocabulary Object Detectors via Multi-Modal Prompt Tuning","created":"2025-11-16","cited_by_count":0,"area":"safety"},{"id":"2511.13545","title":"Robust Defense Strategies for Multimodal Contrastive Learning: Efficient Fine-tuning Against Backdoor Attacks","created":"2025-11-17","cited_by_count":0,"area":"safety"},{"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":"2603.27522","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":"2606.02947","title":"BYORn: Bootstrap Your Own Responses to Defend Large Vision-Language Models Against Backdoor Attacks","created":"2026-06-01","cited_by_count":0,"area":"mllm"},{"id":"2606.17815","title":"Beyond Native Success: Auditing Deployment-Interface Exposure of CLIP Backdoors","created":"2026-06-16","cited_by_count":0,"area":"safety"},{"id":"2607.02995","title":"VISTA: Auditing Semantic Divergence in Vision-Language Models","created":"2026-07-03","cited_by_count":0,"area":"mllm"},{"id":"2607.12571","title":"TrustVLA: Mechanism-Guided Inference-Time Defense Against Vision-Language-Action Backdoors","created":"2026-07-14","cited_by_count":0,"area":"vla"},{"id":"2608.21577","title":"Anchoring Bias: A Persistent Fairness Backdoor Attack against MLLMs under Continual Learning","created":"2026-08-21","cited_by_count":0,"area":"mllm"},{"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":"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"},{"id":"2610.16598","title":"Detecting Chain-of-Thought Hijacking in Backdoored Multimodal Large Reasoning Models","created":"2026-10-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}