{"total":92,"rows":[{"id":"2310.13828","title":"Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models","created":"2023-10-20","cited_by_count":75,"area":"safety"},{"id":"2306.04542","title":"On the Design Fundamentals of Diffusion Models: A Survey","created":"2023-06-07","cited_by_count":60,"area":"diffusion"},{"id":"2305.10701","title":"Personalization as a Shortcut for Few-Shot Backdoor Attack against Text-to-Image Diffusion Models","created":"2023-05-18","cited_by_count":42,"area":"diffusion"},{"id":"2405.14800","title":"Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy","created":"2024-05-23","cited_by_count":38,"area":"diffusion"},{"id":"2307.16489","title":"BAGM: A Backdoor Attack for Manipulating Text-to-Image Generative Models","created":"2023-07-31","cited_by_count":37,"area":"safety"},{"id":"2401.04136","title":"The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright Breaches Without Adjusting Finetuning Pipeline","created":"2024-01-07","cited_by_count":33,"area":"diffusion"},{"id":"2408.03400","title":"Attacks and Defenses for Generative Diffusion Models: A Comprehensive Survey","created":"2024-08-06","cited_by_count":32,"area":"diffusion"},{"id":"2312.00050","title":"Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift","created":"2023-11-27","cited_by_count":31,"area":"diffusion"},{"id":"2412.04852","title":"SleeperMark: Towards Robust Watermark against Fine-Tuning Text-to-image Diffusion Models","created":"2024-12-06","cited_by_count":29,"area":"diffusion"},{"id":"2409.05294","title":"TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors","created":"2024-09-09","cited_by_count":25,"area":"diffusion"},{"id":"2405.08317","title":"SpeechGuard: Exploring the Adversarial Robustness of Multimodal Large Language Models","created":"2024-05-14","cited_by_count":18,"area":"mllm"},{"id":"2312.13053","title":"Quantifying Bias in Text-to-Image Generative Models","created":"2023-12-20","cited_by_count":16,"area":null},{"id":"2307.16680","title":"On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook","created":"2023-07-31","cited_by_count":15,"area":"diffusion"},{"id":"2308.10718","title":"Backdooring Textual Inversion for Concept Censorship","created":"2023-08-21","cited_by_count":14,"area":"diffusion"},{"id":"2404.01101","title":"UFID: A Unified Framework for Input-level Backdoor Detection on Diffusion Models","created":"2024-04-01","cited_by_count":14,"area":"diffusion"},{"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":"2406.15213","title":"Backdooring Bias ($B^2$) into Stable Diffusion Models","created":"2024-06-21","cited_by_count":12,"area":"diffusion"},{"id":"2410.03869","title":"Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Step","created":"2024-10-04","cited_by_count":11,"area":"safety"},{"id":"2503.09669","title":"Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models","created":"2025-03-12","cited_by_count":11,"area":"diffusion"},{"id":"2402.15429","title":"ProTIP: Probabilistic Robustness Verification on Text-to-Image Diffusion Models against Stochastic Perturbation","created":"2024-02-23","cited_by_count":10,"area":"diffusion"},{"id":"2311.02373","title":"From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models","created":"2023-11-04","cited_by_count":9,"area":"diffusion"},{"id":"2412.11441","title":"UIBDiffusion: Universal Imperceptible Backdoor Attack for Diffusion Models","created":"2024-12-16","cited_by_count":9,"area":"diffusion"},{"id":"2504.16907","title":"BadVideo: Stealthy Backdoor Attack against Text-to-Video Generation","created":"2025-04-23","cited_by_count":9,"area":"safety"},{"id":"2504.21072","title":"Erased but Not Forgotten: How Backdoors Compromise Concept Erasure","created":"2025-04-29","cited_by_count":9,"area":"diffusion"},{"id":"2502.11798","title":"BackdoorDM: A Comprehensive Benchmark for Backdoor Learning on Diffusion Model","created":"2025-02-17","cited_by_count":8,"area":"diffusion"},{"id":"2503.06453","title":"Efficient Input-level Backdoor Defense on Text-to-Image Synthesis via Neuron Activation Variation","created":"2025-03-09","cited_by_count":8,"area":"diffusion"},{"id":"2409.12314","title":"Understanding Implosion in Text-to-Image Generative Models","created":"2024-09-18","cited_by_count":6,"area":"diffusion"},{"id":"2409.18214","title":"Trustworthy Text-to-Image Diffusion Models: A Timely and Focused Survey","created":"2024-09-26","cited_by_count":6,"area":"diffusion"},{"id":"2505.08809","title":"MixBridge: Heterogeneous Image-to-Image Backdoor Attack through Mixture of Schr\\\"odinger Bridges","created":"2025-05-12","cited_by_count":6,"area":"diffusion"},{"id":"2312.00057","title":"VA3: Virtually Assured Amplification Attack on Probabilistic Copyright Protection for Text-to-Image Generative Models","created":"2023-11-29","cited_by_count":5,"area":null},{"id":"2406.16272","title":"Repairing Catastrophic-Neglect in Text-to-Image Diffusion Models via Attention-Guided Feature Enhancement","created":"2024-06-24","cited_by_count":5,"area":"diffusion"},{"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":"2505.23518","title":"TRAP: Targeted Redirecting of Agentic Preferences","created":"2025-05-29","cited_by_count":5,"area":"lr"},{"id":"2310.08320","title":"Defending Our Privacy With Backdoors","created":"2023-10-12","cited_by_count":4,"area":null},{"id":"2504.14815","title":"What Lurks Within? Concept Auditing for Shared Diffusion Models at Scale","created":"2025-04-21","cited_by_count":4,"area":"diffusion"},{"id":"2602.21977","title":"When LoRA Betrays: Backdooring Text-to-Image Models by Masquerading as Benign Adapters","created":"2026-02-25","cited_by_count":4,"area":"diffusion"},{"id":"2402.05967","title":"The last Dance : Robust backdoor attack via diffusion models and bayesian approach","created":"2024-02-05","cited_by_count":3,"area":"diffusion"},{"id":"2412.07249","title":"Buster: Implanting Semantic Backdoor into Text Encoder to Mitigate NSFW Content Generation","created":"2024-12-10","cited_by_count":3,"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":"2503.17724","title":"Trigger without Trace: Towards Stealthy Backdoor Attack on Text-to-Image Diffusion Models","created":"2025-03-22","cited_by_count":3,"area":"diffusion"},{"id":"2504.20518","title":"Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models","created":"2025-04-29","cited_by_count":3,"area":"diffusion"},{"id":"2509.22723","title":"Responsible Diffusion: A Comprehensive Survey on Safety, Ethics, and Trust in Diffusion Models","created":"2025-09-25","cited_by_count":3,"area":"diffusion"},{"id":"2405.00466","title":"Lazy Layers to Make Fine-Tuned Diffusion Models More Traceable","created":"2024-05-01","cited_by_count":2,"area":"diffusion"},{"id":"2411.12389","title":"Combinational Backdoor Attack against Customized Text-to-Image Models","created":"2024-11-19","cited_by_count":2,"area":"diffusion"},{"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":"2504.05815","title":"Parasite: A Steganography-based Backdoor Attack Framework for Diffusion Models","created":"2025-04-08","cited_by_count":2,"area":"diffusion"},{"id":"2504.18563","title":"Backdoor Defense in Diffusion Models via Spatial Attention Unlearning","created":"2025-04-21","cited_by_count":2,"area":"diffusion"},{"id":"2505.02824","title":"Towards Dataset Copyright Evasion Attack against Personalized Text-to-Image Diffusion Models","created":"2025-05-05","cited_by_count":2,"area":"diffusion"},{"id":"2506.03234","title":"BadReward: Clean-Label Poisoning of Reward Models in Text-to-Image RLHF","created":"2025-06-03","cited_by_count":2,"area":"alignment"},{"id":"2508.18235","title":"Sealing The Backdoor: Unlearning Adversarial Text Triggers In Diffusion Models Using Knowledge Distillation","created":"2025-08-20","cited_by_count":2,"area":"diffusion"},{"id":"2605.09005","title":"Towards Backdoor-Based Ownership Verification for Vision-Language-Action Models","created":"2026-05-09","cited_by_count":2,"area":"vla"},{"id":"2406.15863","title":"EmoAttack: Emotion-to-Image Diffusion Models for Emotional Backdoor Generation","created":"2024-06-22","cited_by_count":1,"area":"diffusion"},{"id":"2411.14681","title":"TrojanEdit: Multimodal Backdoor Attack Against Image Editing Model","created":"2024-11-22","cited_by_count":1,"area":"diffusion"},{"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":"2502.20650","title":"Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models","created":"2025-02-28","cited_by_count":1,"area":"diffusion"},{"id":"2505.15308","title":"BadSR: Stealthy Label Backdoor Attacks on Image Super-Resolution","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2506.21874","title":"On the Feasibility of Poisoning Text-to-Image AI Models via Adversarial Mislabeling","created":"2025-06-27","cited_by_count":1,"area":"mllm"},{"id":"2507.04726","title":"Backdoors in Conditional Diffusion: Threats to Responsible Synthetic Data Pipelines","created":"2025-07-07","cited_by_count":1,"area":"diffusion"},{"id":"2508.01605","title":"Practical, Generalizable and Robust Backdoor Attacks on Text-to-Image Diffusion Models","created":"2025-08-03","cited_by_count":1,"area":"diffusion"},{"id":"2603.05921","title":"BlackMirror: Black-Box Backdoor Detection for Text-to-Image Models via Instruction-Response Deviation","created":"2026-03-06","cited_by_count":1,"area":"safety"},{"id":"2605.19227","title":"Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models","created":"2026-05-19","cited_by_count":1,"area":"safety"},{"id":"2605.29434","title":"AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasing","created":"2026-05-28","cited_by_count":1,"area":"safety"},{"id":"2311.09680","title":"Trustworthy Large Models in Vision: A Survey","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2404.02530","title":"Manipulating and Mitigating Generative Model Biases without Retraining","created":"2024-04-03","cited_by_count":0,"area":"safety"},{"id":"2406.13933","title":"EnTruth: Enhancing the Traceability of Unauthorized Dataset Usage in Text-to-image Diffusion Models with Minimal and Robust Alterations","created":"2024-06-20","cited_by_count":0,"area":"diffusion"},{"id":"2504.21042","title":"What's Pulling the Strings? Evaluating Integrity and Attribution in AI Training and Inference through Concept Shift","created":"2025-04-28","cited_by_count":0,"area":"safety"},{"id":"2508.03221","title":"BadBlocks: Low-Cost and Stealthy Backdoor Attacks Tailored for Text-to-Image Diffusion Models","created":"2025-08-05","cited_by_count":0,"area":"diffusion"},{"id":"2510.00293","title":"MOLM: Mixture of LoRA Markers","created":"2025-09-30","cited_by_count":0,"area":"safety"},{"id":"2510.20792","title":"BadGraph: A Backdoor Attack Against Latent Diffusion Model for Text-Guided Graph Generation","created":"2025-10-23","cited_by_count":0,"area":"diffusion"},{"id":"2601.17379","title":"Prompt and Circumstances: Evaluating the Efficacy of Human Prompt Inference in AI-Generated Art","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2602.01765","title":"Backdoor Sentinel: Detecting and Detoxifying Backdoors in Diffusion Models via Temporal Noise Consistency","created":"2026-02-02","cited_by_count":0,"area":"diffusion"},{"id":"2602.04898","title":"Semantic-level Backdoor Attack against Text-to-Image Diffusion Models","created":"2026-02-03","cited_by_count":0,"area":"diffusion"},{"id":"2602.20193","title":"When Backdoors Go Beyond Triggers: Semantic Drift in Diffusion Models Under Encoder Attacks","created":"2026-02-21","cited_by_count":0,"area":"diffusion"},{"id":"2603.04064","title":"Tuning Just Enough: Lightweight Backdoor Attacks on Multi-Encoder Diffusion Models","created":"2026-03-04","cited_by_count":0,"area":"diffusion"},{"id":"2603.06508","title":"When One Modality Rules Them All: Backdoor Modality Collapse in Multimodal Diffusion Models","created":"2026-03-06","cited_by_count":0,"area":"diffusion"},{"id":"2603.17513","title":"Proof-of-Authorship for Diffusion-based AI Generated Content","created":"2026-03-18","cited_by_count":0,"area":"diffusion"},{"id":"2604.12446","title":"Scaling Exposes the Trigger: Input-Level Backdoor Detection in Text-to-Image Diffusion Models via Cross-Attention Scaling","created":"2026-04-14","cited_by_count":0,"area":"diffusion"},{"id":"2605.00935","title":"Watch Your Step: Information Injection in Diffusion Models via Shadow Timestep Embedding","created":"2026-05-01","cited_by_count":0,"area":"diffusion"},{"id":"2605.07399","title":"GPO-V: Jailbreak Diffusion Vision Language Model by Global Probability Optimization","created":"2026-05-08","cited_by_count":0,"area":"mllm"},{"id":"2605.08280","title":"Beyond the False Trade-off: Adaptive EWC for Stealthy and Generalizable T2I Backdoors","created":"2026-05-08","cited_by_count":0,"area":"safety"},{"id":"2605.09397","title":"BadDLM: Backdooring Diffusion Language Models with Diverse Targets","created":"2026-05-10","cited_by_count":0,"area":"diffusion"},{"id":"2605.13115","title":"DiffusionHijack: Supply-Chain PRNG Backdoor Attack on Diffusion Models and Quantum Random Number Defense","created":"2026-05-13","cited_by_count":0,"area":"diffusion"},{"id":"2605.19262","title":"Backdooring Masked Diffusion Language Models","created":"2026-05-19","cited_by_count":0,"area":"diffusion"},{"id":"2605.19698","title":"Awakening the Hydra: Stabilizing Multi-Concept Backdoor Injection in Text-to-Image Diffusion Models","created":"2026-05-19","cited_by_count":0,"area":"diffusion"},{"id":"2606.23362","title":"TooBad: Backdoor Diffusion Models with Ultra-Low Poison Rate and Imperceptible Trigger","created":"2026-06-22","cited_by_count":0,"area":"diffusion"},{"id":"2606.29759","title":"GoodDiffusion: Proactive Copyright Protection for Diffusion Bridge Models via Learnable Sample-specific Signatures","created":"2026-06-29","cited_by_count":0,"area":"safety"},{"id":"2607.25479","title":"Architectural Backdoors in Vision-Language Model Supply Chains via Representation Steering","created":"2026-07-28","cited_by_count":0,"area":"mllm"},{"id":"2608.00543","title":"Robust Watermarks Meet Backdoored Models: Evading Diffusion Semantic Watermarks via Stealthy Backdoor","created":"2026-08-01","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":"2609.00873","title":"Membership Inference in Fine-tuned Diffusion Language Models via Token-level Memorization Asymmetry","created":"2026-09-01","cited_by_count":0,"area":"diffusion"},{"id":"2609.25884","title":"LoRango: It Takes Two LoRAs to Unlock Hidden Behaviors in Diffusion Models","created":"2026-09-22","cited_by_count":0,"area":"diffusion"},{"id":"2609.39047","title":"BadAction: Backdoor Attacks on Interactive Video Generation via Action-Guided Triggers","created":"2026-09-30","cited_by_count":0,"area":"safety"}],"next_cursor":null}