{"total":262,"rows":[{"id":"2310.10844","title":"Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks","created":"2023-10-16","cited_by_count":194,"area":"safety"},{"id":"2308.10741","title":"On the Adversarial Robustness of Multi-Modal Foundation Models","created":"2023-08-21","cited_by_count":145,"area":"safety"},{"id":"2504.11358","title":"DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks","created":"2025-04-15","cited_by_count":143,"area":"safety"},{"id":"2108.00352","title":"BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning","created":"2021-08-01","cited_by_count":123,"area":"safety"},{"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":"2311.04378","title":"Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models","created":"2023-11-07","cited_by_count":87,"area":"safety"},{"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":"2108.11023","title":"EncoderMI: Membership Inference against Pre-trained Encoders in Contrastive Learning","created":"2021-08-25","cited_by_count":73,"area":"safety"},{"id":"2210.00968","title":"Membership Inference Attacks Against Text-to-image Generation Models","created":"2022-10-03","cited_by_count":69,"area":"safety"},{"id":"2303.03323","title":"CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning","created":"2023-03-06","cited_by_count":63,"area":"safety"},{"id":"2406.05498","title":"SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner","created":"2024-06-08","cited_by_count":63,"area":"safety"},{"id":"2302.04237","title":"Black Box Adversarial Prompting for Foundation Models","created":"2023-02-08","cited_by_count":62,"area":"safety"},{"id":"2403.01446","title":"GuardT2I: Defending Text-to-Image Models from Adversarial Prompts","created":"2024-03-03","cited_by_count":62,"area":"safety"},{"id":"2211.02408","title":"Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis","created":"2022-11-04","cited_by_count":59,"area":"safety"},{"id":"2303.15180","title":"Detecting Backdoors in Pre-trained Encoders","created":"2023-03-23","cited_by_count":55,"area":"safety"},{"id":"2411.18479","title":"SoK: Watermarking for AI-Generated Content","created":"2024-11-27","cited_by_count":51,"area":"safety"},{"id":"2407.21035","title":"Direct Unlearning Optimization for Robust and Safe Text-to-Image Models","created":"2024-07-17","cited_by_count":50,"area":"safety"},{"id":"2407.20516","title":"Machine Unlearning in Generative AI: A Survey","created":"2024-07-30","cited_by_count":49,"area":"safety"},{"id":"2402.00351","title":"Machine Unlearning for Image-to-Image Generative Models","created":"2024-02-01","cited_by_count":47,"area":"safety"},{"id":"2206.03693","title":"Autoregressive Perturbations for Data Poisoning","created":"2022-06-08","cited_by_count":46,"area":"safety"},{"id":"2106.14851","title":"Data Poisoning Won't Save You From Facial Recognition","created":"2021-06-28","cited_by_count":45,"area":"safety"},{"id":"2305.06321","title":"SepMark: Deep Separable Watermarking for Unified Source Tracing and Deepfake Detection","created":"2023-05-10","cited_by_count":44,"area":"safety"},{"id":"2209.15266","title":"Data Poisoning Attacks Against Multimodal Encoders","created":"2022-09-30","cited_by_count":41,"area":"safety"},{"id":"2408.10848","title":"Perception-guided Jailbreak against Text-to-Image Models","created":"2024-08-20","cited_by_count":40,"area":"safety"},{"id":"2410.18057","title":"CLEAR: Character Unlearning in Textual and Visual Modalities","created":"2024-10-23","cited_by_count":39,"area":"safety"},{"id":"2310.00108","title":"Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study","created":"2023-09-29","cited_by_count":38,"area":"safety"},{"id":"2311.15766","title":"Knowledge Unlearning for LLMs: Tasks, Methods, and Challenges","created":"2023-11-27","cited_by_count":38,"area":"safety"},{"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":"2202.11202","title":"Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning","created":"2022-02-22","cited_by_count":34,"area":"safety"},{"id":"2205.06401","title":"PoisonedEncoder: Poisoning the Unlabeled Pre-training Data in Contrastive Learning","created":"2022-05-13","cited_by_count":34,"area":"safety"},{"id":"2404.12916","title":"Physical Backdoor Attack can Jeopardize Driving with Vision-Large-Language Models","created":"2024-04-19","cited_by_count":33,"area":"safety"},{"id":"2305.17444","title":"Query-Efficient Black-Box Red Teaming via Bayesian Optimization","created":"2023-05-27","cited_by_count":32,"area":"safety"},{"id":"2411.09259","title":"Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey","created":"2024-11-14","cited_by_count":32,"area":"safety"},{"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":"2211.08229","title":"CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning","created":"2022-11-15","cited_by_count":29,"area":"safety"},{"id":"2306.07754","title":"Generative Watermarking Against Unauthorized Subject-Driven Image Synthesis","created":"2023-06-13","cited_by_count":23,"area":"safety"},{"id":"2405.16567","title":"Automatic Jailbreaking of the Text-to-Image Generative AI Systems","created":"2024-05-26","cited_by_count":23,"area":"safety"},{"id":"2406.09408","title":"Data Attribution for Text-to-Image Models by Unlearning Synthesized Images","created":"2024-06-13","cited_by_count":22,"area":"safety"},{"id":"2302.10894","title":"Red Teaming Deep Neural Networks with Feature Synthesis Tools","created":"2023-02-08","cited_by_count":21,"area":"safety"},{"id":"2311.12047","title":"MultiDelete for Multimodal Machine Unlearning","created":"2023-11-18","cited_by_count":20,"area":"safety"},{"id":"2510.14005","title":"PIShield: Detecting Prompt Injection Attacks via Intrinsic LLM Features","created":"2025-10-15","cited_by_count":20,"area":"safety"},{"id":"2110.13541","title":"Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes","created":"2021-10-26","cited_by_count":19,"area":"safety"},{"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":"2407.07735","title":"Protecting NeRFs' Copyright via Plug-And-Play Watermarking Base Model","created":"2024-07-10","cited_by_count":18,"area":"safety"},{"id":"2407.11867","title":"Targeted Unlearning with Single Layer Unlearning Gradient","created":"2024-07-16","cited_by_count":18,"area":"safety"},{"id":"2504.15512","title":"T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models","created":"2025-04-22","cited_by_count":18,"area":"safety"},{"id":"2210.06516","title":"How to Sift Out a Clean Data Subset in the Presence of Data Poisoning?","created":"2022-10-12","cited_by_count":17,"area":"safety"},{"id":"2403.09914","title":"ProMark: Proactive Diffusion Watermarking for Causal Attribution","created":"2024-03-14","cited_by_count":17,"area":"safety"},{"id":"2407.07485","title":"Zero-Shot Class Unlearning in CLIP with Synthetic Samples","created":"2024-07-10","cited_by_count":17,"area":"safety"},{"id":"2411.15537","title":"MUNBa: Machine Unlearning via Nash Bargaining","created":"2024-11-23","cited_by_count":17,"area":"safety"},{"id":"2501.03544","title":"PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models","created":"2025-01-07","cited_by_count":17,"area":"safety"},{"id":"2604.20358","title":"ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval","created":"2026-04-22","cited_by_count":17,"area":"safety"},{"id":"2401.10458","title":"Contrastive Unlearning: A Contrastive Approach to Machine Unlearning","created":"2024-01-19","cited_by_count":15,"area":"safety"},{"id":"2507.06908","title":"MIND: A Multi-agent Framework for Zero-shot Harmful Meme Detection","created":"2025-07-09","cited_by_count":15,"area":"safety"},{"id":"2410.03489","title":"Gradient-based Jailbreak Images for Multimodal Fusion Models","created":"2024-10-04","cited_by_count":14,"area":"safety"},{"id":"2312.02052","title":"DUCK: Distance-based Unlearning via Centroid Kinematics","created":"2023-12-04","cited_by_count":13,"area":"safety"},{"id":"2409.17601","title":"CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning","created":"2024-09-26","cited_by_count":13,"area":"safety"},{"id":"2408.00376","title":"On the Limitations and Prospects of Machine Unlearning for Generative AI","created":"2024-08-01","cited_by_count":12,"area":"safety"},{"id":"2412.20392","title":"Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning","created":"2024-12-29","cited_by_count":12,"area":"safety"},{"id":"2503.09117","title":"GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs","created":"2025-03-12","cited_by_count":12,"area":"safety"},{"id":"2504.05058","title":"Not All Data Are Unlearned Equally","created":"2025-04-07","cited_by_count":12,"area":"safety"},{"id":"2509.22292","title":"Jailbreaking on Text-to-Video Models via Scene Splitting Strategy","created":"2025-09-26","cited_by_count":12,"area":"safety"},{"id":"2405.15495","title":"Towards Natural Machine Unlearning","created":"2024-05-24","cited_by_count":11,"area":"safety"},{"id":"2405.17878","title":"An Information Theoretic Evaluation Metric For Strong Unlearning","created":"2024-05-28","cited_by_count":11,"area":"safety"},{"id":"2305.14851","title":"Sharpness-Aware Data Poisoning Attack","created":"2023-05-24","cited_by_count":10,"area":"safety"},{"id":"2311.15268","title":"Unlearning via Sparse Representations","created":"2023-11-26","cited_by_count":10,"area":"safety"},{"id":"2409.15968","title":"Adversarial Backdoor Defense in CLIP","created":"2024-09-24","cited_by_count":10,"area":"safety"},{"id":"2410.18371","title":"Gibberish is All You Need for Membership Inference Detection in Contrastive Language-Audio Pretraining","created":"2024-10-24","cited_by_count":10,"area":"safety"},{"id":"2410.05583","title":"NegMerge: Sign-Consensual Weight Merging for Machine Unlearning","created":"2024-10-08","cited_by_count":9,"area":"safety"},{"id":"2504.11106","title":"Token-Level Constraint Boundary Search for Jailbreaking Text-to-Image Models","created":"2025-04-15","cited_by_count":9,"area":"safety"},{"id":"2506.02761","title":"Rethinking Machine Unlearning in Image Generation Models","created":"2025-06-03","cited_by_count":9,"area":"safety"},{"id":"2508.03696","title":"PLA: Prompt Learning Attack against Text-to-Image Generative Models","created":"2025-07-14","cited_by_count":9,"area":"safety"},{"id":"2309.05940","title":"Catch You Everything Everywhere: Guarding Textual Inversion via Concept Watermarking","created":"2023-09-12","cited_by_count":8,"area":"safety"},{"id":"2310.07726","title":"Warfare:Breaking the Watermark Protection of AI-Generated Content","created":"2023-09-27","cited_by_count":8,"area":"safety"},{"id":"2402.12626","title":"Indiscriminate Data Poisoning Attacks on Pre-trained Feature Extractors","created":"2024-02-20","cited_by_count":8,"area":"safety"},{"id":"2403.18774","title":"RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees","created":"2024-01-23","cited_by_count":8,"area":"safety"},{"id":"2406.03508","title":"Mutual Information Guided Backdoor Mitigation for Pre-trained Encoders","created":"2024-06-05","cited_by_count":8,"area":"safety"},{"id":"2502.00718","title":"\"I am bad\": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models","created":"2025-02-02","cited_by_count":8,"area":"safety"},{"id":"2505.21074","title":"Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling","created":"2025-05-27","cited_by_count":8,"area":"safety"},{"id":"2406.19395","title":"Dataset Size Recovery from LoRA Weights","created":"2024-06-27","cited_by_count":7,"area":"safety"},{"id":"2407.02411","title":"Video Watermarking: Safeguarding Your Video from (Unauthorized) Annotations by Video-based LLMs","created":"2024-07-02","cited_by_count":7,"area":"safety"},{"id":"2408.00352","title":"Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motion","created":"2024-08-01","cited_by_count":7,"area":"safety"},{"id":"2409.14747","title":"Distribution-Level Feature Distancing for Machine Unlearning: Towards a Better Trade-off Between Model Utility and Forgetting","created":"2024-09-23","cited_by_count":7,"area":"safety"},{"id":"2411.13553","title":"AI-generated Image Detection: Passive or Watermark?","created":"2024-11-20","cited_by_count":7,"area":"safety"},{"id":"2503.02312","title":"Go Beyond Your Means: Unlearning with Per-Sample Gradient Orthogonalization","created":"2025-03-04","cited_by_count":7,"area":"safety"},{"id":"2504.15548","title":"LLM-based Semantic Augmentation for Harmful Content Detection","created":"2025-04-22","cited_by_count":7,"area":"safety"},{"id":"2506.23484","title":"TAG-WM: Tamper-Aware Generative Image Watermarking via Diffusion Inversion Sensitivity","created":"2025-06-30","cited_by_count":7,"area":"safety"},{"id":"2509.11745","title":"Removal Attack and Defense on AI-generated Content Latent-based Watermarking","created":"2025-09-15","cited_by_count":7,"area":"safety"},{"id":"2511.07210","title":"Breaking the Stealth-Potency Trade-off in Clean-Image Backdoors with Generative Trigger Optimization","created":"2025-11-10","cited_by_count":7,"area":"safety"},{"id":"2601.02751","title":"Window-based Membership Inference Attacks Against Fine-tuned Large Language Models","created":"2026-01-06","cited_by_count":7,"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":"2405.15662","title":"Class Machine Unlearning for Complex Data via Concepts Inference and Data Poisoning","created":"2024-05-24","cited_by_count":6,"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":"2506.03117","title":"Targeted Forgetting of Image Subgroups in CLIP Models","created":"2025-06-03","cited_by_count":6,"area":"safety"},{"id":"2506.23731","title":"Radioactive Watermarks in Diffusion and Autoregressive Image Generative Models","created":"2025-06-30","cited_by_count":6,"area":"safety"},{"id":"2507.21412","title":"Cascading and Proxy Membership Inference Attacks","created":"2025-07-29","cited_by_count":6,"area":"safety"},{"id":"2510.05173","title":"SafeGuider: Robust and Practical Content Safety Control for Text-to-Image Models","created":"2025-10-05","cited_by_count":6,"area":"safety"},{"id":"2511.19339","title":"POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse","created":"2025-11-24","cited_by_count":6,"area":"safety"},{"id":"2603.01228","title":"Towards Policy-Adaptive Image Guardrail: Benchmark and Method","created":"2026-03-01","cited_by_count":6,"area":"safety"}],"next_cursor":"100"}