{"total":67,"rows":[{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"2302.10149","title":"Poisoning Web-Scale Training Datasets is Practical","created":"2023-02-20","cited_by_count":290,"area":null},{"id":"2305.00944","title":"Poisoning Language Models During Instruction Tuning","created":"2023-05-01","cited_by_count":269,"area":null},{"id":"2202.03423","title":"Backdoor Defense via Decoupling the Training Process","created":"2022-02-05","cited_by_count":153,"area":null},{"id":"2205.14459","title":"CyCLIP: Cyclic Contrastive Language-Image Pretraining","created":"2022-05-28","cited_by_count":127,"area":null},{"id":"2308.14840","title":"Identifying and Mitigating the Security Risks of Generative AI","created":"2023-08-28","cited_by_count":91,"area":null},{"id":"2110.11316","title":"CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP","created":"2021-10-21","cited_by_count":89,"area":null},{"id":"2205.13383","title":"BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning","created":"2022-05-26","cited_by_count":86,"area":null},{"id":"2210.00875","title":"Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection","created":"2022-09-27","cited_by_count":86,"area":null},{"id":"2303.12175","title":"Black-box Backdoor Defense via Zero-shot Image Purification","created":"2023-03-21","cited_by_count":45,"area":null},{"id":"2111.08429","title":"An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defences","created":"2021-11-16","cited_by_count":42,"area":null},{"id":"2202.06382","title":"Training with More Confidence: Mitigating Injected and Natural Backdoors During Training","created":"2022-02-13","cited_by_count":38,"area":null},{"id":"2303.06818","title":"Backdoor Defense via Deconfounded Representation Learning","created":"2023-03-13","cited_by_count":38,"area":null},{"id":"2307.12280","title":"Downstream-agnostic Adversarial Examples","created":"2023-07-23","cited_by_count":32,"area":null},{"id":"2310.01875","title":"Towards Stable Backdoor Purification through Feature Shift Tuning","created":"2023-10-03","cited_by_count":32,"area":null},{"id":"2210.07346","title":"An Embarrassingly Simple Backdoor Attack on Self-supervised Learning","created":"2022-10-13","cited_by_count":31,"area":null},{"id":"2302.11408","title":"ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning Paradigms","created":"2023-02-22","cited_by_count":29,"area":null},{"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":"2311.12202","title":"Nepotistically Trained Generative-AI Models Collapse","created":"2023-11-20","cited_by_count":27,"area":null},{"id":"2201.05889","title":"StolenEncoder: Stealing Pre-trained Encoders in Self-supervised Learning","created":"2022-01-15","cited_by_count":23,"area":null},{"id":"2301.01197","title":"Backdoor Attacks Against Dataset Distillation","created":"2023-01-03","cited_by_count":21,"area":null},{"id":"2305.11596","title":"Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation","created":"2023-05-19","cited_by_count":21,"area":null},{"id":"2304.01482","title":"Defending Against Patch-based Backdoor Attacks on Self-Supervised Learning","created":"2023-04-04","cited_by_count":20,"area":null},{"id":"2405.19524","title":"AI Risk Management Should Incorporate Both Safety and Security","created":"2024-05-29","cited_by_count":17,"area":null},{"id":"2202.10627","title":"On the Effectiveness of Adversarial Training against Backdoor Attacks","created":"2022-02-22","cited_by_count":16,"area":null},{"id":"2210.06428","title":"Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork","created":"2022-10-12","cited_by_count":12,"area":null},{"id":"2301.12576","title":"Uncovering Adversarial Risks of Test-Time Adaptation","created":"2023-01-29","cited_by_count":12,"area":null},{"id":"2201.08217","title":"Watermarking Pre-trained Encoders in Contrastive Learning","created":"2022-01-20","cited_by_count":11,"area":null},{"id":"2109.04699","title":"EfficientCLIP: Efficient Cross-Modal Pre-training by Ensemble Confident Learning and Language Modeling","created":"2021-09-10","cited_by_count":10,"area":null},{"id":"2301.10576","title":"A Study on FGSM Adversarial Training for Neural Retrieval","created":"2023-01-25","cited_by_count":10,"area":null},{"id":"2303.00215","title":"Single Image Backdoor Inversion via Robust Smoothed Classifiers","created":"2023-03-01","cited_by_count":10,"area":null},{"id":"2403.19326","title":"MedBN: Robust Test-Time Adaptation against Malicious Test Samples","created":"2024-03-28","cited_by_count":10,"area":null},{"id":"2312.09057","title":"On the Difficulty of Defending Contrastive Learning against Backdoor Attacks","created":"2023-12-14","cited_by_count":9,"area":null},{"id":"2411.11667","title":"Dissecting Representation Misalignment in Contrastive Learning via Influence Function","created":"2024-11-18","cited_by_count":8,"area":null},{"id":"2210.01632","title":"Backdoor Attacks in the Supply Chain of Masked Image Modeling","created":"2022-10-04","cited_by_count":7,"area":null},{"id":"2410.09838","title":"Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense","created":"2024-10-13","cited_by_count":7,"area":null},{"id":"2412.06219","title":"Data Free Backdoor Attacks","created":"2024-12-09","cited_by_count":7,"area":null},{"id":"2110.15444","title":"10 Security and Privacy Problems in Large Foundation Models","created":"2021-10-28","cited_by_count":6,"area":null},{"id":"2405.14672","title":"Invisible Backdoor Attack against Self-supervised Learning","created":"2024-05-23","cited_by_count":6,"area":null},{"id":"2207.04209","title":"Invisible Backdoor Attacks Using Data Poisoning in the Frequency Domain","created":"2022-07-09","cited_by_count":5,"area":null},{"id":"2308.09490","title":"Balancing Transparency and Risk: The Security and Privacy Risks of Open-Source Machine Learning Models","created":"2023-08-18","cited_by_count":5,"area":null},{"id":"2211.07122","title":"ContextCLIP: Contextual Alignment of Image-Text pairs on CLIP visual representations","created":"2022-11-14","cited_by_count":4,"area":null},{"id":"2310.08320","title":"Defending Our Privacy With Backdoors","created":"2023-10-12","cited_by_count":4,"area":null},{"id":"2301.02905","title":"REaaS: Enabling Adversarially Robust Downstream Classifiers via Robust Encoder as a Service","created":"2023-01-07","cited_by_count":3,"area":null},{"id":"2310.10665","title":"Privacy Preservation in Artificial Intelligence and Extended Reality (AI-XR) Metaverses: A Survey","created":"2023-09-19","cited_by_count":3,"area":null},{"id":"2405.11575","title":"SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks","created":"2024-05-19","cited_by_count":3,"area":null},{"id":"2409.15126","title":"UTrace: Poisoning Forensics for Private Collaborative Learning","created":"2024-09-23","cited_by_count":3,"area":null},{"id":"2205.09586","title":"On Trace of PGD-Like Adversarial Attacks","created":"2022-05-19","cited_by_count":2,"area":null},{"id":"2312.07955","title":"Erasing Self-Supervised Learning Backdoor by Cluster Activation Masking","created":"2023-12-13","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":"2507.12022","title":"Dataset Ownership Verification for Pre-trained Masked Models","created":"2025-07-16","cited_by_count":2,"area":null},{"id":"2308.04673","title":"SSL-Auth: An Authentication Framework by Fragile Watermarking for Pre-trained Encoders in Self-supervised Learning","created":"2023-08-09","cited_by_count":1,"area":null},{"id":"2404.06694","title":"How to Craft Backdoors with Unlabeled Data Alone?","created":"2024-04-10","cited_by_count":1,"area":null},{"id":"2408.00129","title":"Vera Verto: Multimodal Hijacking Attack","created":"2024-07-31","cited_by_count":1,"area":null},{"id":"2408.01705","title":"Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers","created":"2024-08-03","cited_by_count":1,"area":null},{"id":"2409.08509","title":"Exploiting Supervised Poison Vulnerability to Strengthen Self-Supervised Defense","created":"2024-09-13","cited_by_count":1,"area":null},{"id":"2411.00519","title":"Outlier-Oriented Poisoning Attack: A Grey-box Approach to Disturb Decision Boundaries by Perturbing Outliers in Multiclass Learning","created":"2024-11-01","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":"2602.09757","title":"Towards Poisoning Robustness Certification for Natural Language Generation","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2311.09680","title":"Trustworthy Large Models in Vision: A Survey","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2408.02814","title":"Pre-trained Encoder Inference: Revealing Upstream Encoders In Downstream Machine Learning Services","created":"2024-08-05","cited_by_count":0,"area":null},{"id":"2505.00881","title":"Protocol-agnostic and Data-free Backdoor Attacks on Pre-trained Models in RF Fingerprinting","created":"2025-05-01","cited_by_count":0,"area":null},{"id":"2506.00242","title":"Whispers of Many Shores: Cultural Alignment through Collaborative Cultural Expertise","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2601.11006","title":"Backdoor Attacks on Multi-modal Contrastive Learning","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2605.01298","title":"Checkerboard: Closed-Form and Data-Independent Trigger Design for Clean-Label Backdoor Attacks","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2605.01834","title":"Repurposing and Evaluating the (In)Feasibility of Dataset Poisoning enabled Watermarking for Contrastive Learning","created":"2026-05-03","cited_by_count":0,"area":null},{"id":"2609.29099","title":"TraceGuard: Adaptive Multimodal Poison Filtering through Cross-Feature Rank Agreement","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}