{"total":103,"rows":[{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154,"area":"alignment"},{"id":"2305.00054","title":"LAVA: Data Valuation without Pre-Specified Learning Algorithms","created":"2023-04-28","cited_by_count":69,"area":null},{"id":"2210.09545","title":"Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models","created":"2022-10-18","cited_by_count":57,"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":"2405.09786","title":"IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency","created":"2024-05-16","cited_by_count":39,"area":null},{"id":"2310.14480","title":"Attention-Enhancing Backdoor Attacks Against BERT-based Models","created":"2023-10-23","cited_by_count":32,"area":"safety"},{"id":"2402.14968","title":"Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment","created":"2024-02-22","cited_by_count":31,"area":null},{"id":"2408.02882","title":"Compromising Embodied Agents with Contextual Backdoor Attacks","created":"2024-08-06","cited_by_count":31,"area":"agents"},{"id":"2307.08208","title":"Towards Stealthy Backdoor Attacks against Speech Recognition via Elements of Sound","created":"2023-07-17","cited_by_count":30,"area":"safety"},{"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":"2311.13091","title":"Stable Unlearnable Example: Enhancing the Robustness of Unlearnable Examples via Stable Error-Minimizing Noise","created":"2023-11-22","cited_by_count":25,"area":null},{"id":"2410.10437","title":"Towards Reliable Verification of Unauthorized Data Usage in Personalized Text-to-Image Diffusion Models","created":"2024-10-14","cited_by_count":20,"area":"diffusion"},{"id":"2501.18617","title":"DarkMind: Latent Chain-of-Thought Backdoor in Customized LLMs","created":"2025-01-24","cited_by_count":20,"area":"lr"},{"id":"2407.13863","title":"A Closer Look at GAN Priors: Exploiting Intermediate Features for Enhanced Model Inversion Attacks","created":"2024-07-18","cited_by_count":18,"area":null},{"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":"2405.19524","title":"AI Risk Management Should Incorporate Both Safety and Security","created":"2024-05-29","cited_by_count":17,"area":null},{"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":"2505.19840","title":"One Surrogate to Fool Them All: Universal, Transferable, and Targeted Adversarial Attacks with CLIP","created":"2025-05-26","cited_by_count":15,"area":null},{"id":"2409.13864","title":"Persistent Backdoor Attacks in Continual Learning","created":"2024-09-20","cited_by_count":13,"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":"2208.13893","title":"Data Isotopes for Data Provenance in DNNs","created":"2022-08-29","cited_by_count":11,"area":null},{"id":"2307.15539","title":"Beating Backdoor Attack at Its Own Game","created":"2023-07-28","cited_by_count":11,"area":null},{"id":"2406.00588","title":"Generalization Bound and New Algorithm for Clean-Label Backdoor Attack","created":"2024-06-02","cited_by_count":11,"area":null},{"id":"2302.03684","title":"Temporal Robustness against Data Poisoning","created":"2023-02-07","cited_by_count":10,"area":"safety"},{"id":"2312.09665","title":"FlowMur: A Stealthy and Practical Audio Backdoor Attack with Limited Knowledge","created":"2023-12-15","cited_by_count":10,"area":null},{"id":"2306.02368","title":"Revisiting Data-Free Knowledge Distillation with Poisoned Teachers","created":"2023-06-04","cited_by_count":9,"area":"safety"},{"id":"2309.06981","title":"MASTERKEY: Practical Backdoor Attack Against Speaker Verification Systems","created":"2023-09-13","cited_by_count":8,"area":null},{"id":"2306.08386","title":"Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios","created":"2023-06-14","cited_by_count":7,"area":null},{"id":"2501.05928","title":"Towards Backdoor Stealthiness in Model Parameter Space","created":"2025-01-10","cited_by_count":7,"area":null},{"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":"2405.14672","title":"Invisible Backdoor Attack against Self-supervised Learning","created":"2024-05-23","cited_by_count":6,"area":null},{"id":"2502.19770","title":"TAPE: Tailored Posterior Difference for Auditing of Machine Unlearning","created":"2025-02-27","cited_by_count":6,"area":"safety"},{"id":"2205.11736","title":"Towards a Defense Against Federated Backdoor Attacks Under Continuous Training","created":"2022-05-24","cited_by_count":5,"area":null},{"id":"2306.08313","title":"A Proxy Attack-Free Strategy for Practically Improving the Poisoning Efficiency in Backdoor Attacks","created":"2023-06-14","cited_by_count":5,"area":null},{"id":"2307.07328","title":"Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategy","created":"2023-07-14","cited_by_count":5,"area":null},{"id":"2301.12318","title":"Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineering","created":"2023-01-29","cited_by_count":4,"area":null},{"id":"2310.07632","title":"Prompt Backdoors in Visual Prompt Learning","created":"2023-10-11","cited_by_count":4,"area":"safety"},{"id":"2407.10825","title":"Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks","created":"2024-07-15","cited_by_count":4,"area":null},{"id":"2407.19203","title":"Clean-Label Physical Backdoor Attacks with Data Distillation","created":"2024-07-27","cited_by_count":4,"area":null},{"id":"2409.06280","title":"Anonymity Unveiled: A Practical Framework for Auditing Data Use in Deep Learning Models","created":"2024-09-10","cited_by_count":4,"area":null},{"id":"2601.11207","title":"LoRA as Oracle","created":"2026-01-16","cited_by_count":4,"area":"safety"},{"id":"2304.10985","title":"INK: Inheritable Natural Backdoor Attack Against Model Distillation","created":"2023-04-21","cited_by_count":3,"area":null},{"id":"2405.18627","title":"PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics","created":"2024-05-28","cited_by_count":3,"area":"diffusion"},{"id":"2501.02373","title":"BADTV: Unveiling Backdoor Threats in Third-Party Task Vectors","created":"2025-01-04","cited_by_count":3,"area":"safety"},{"id":"2507.06262","title":"Q-Detection: A Quantum-Classical Hybrid Poisoning Attack Detection Method","created":"2025-07-07","cited_by_count":3,"area":null},{"id":"2512.08129","title":"Improving the Sensitivity of Backdoor Detectors via Class Subspace Orthogonalization","created":"2025-12-09","cited_by_count":3,"area":null},{"id":"2605.02202","title":"CBV: Clean-label Backdoor Attacks on Vision Language Models via Diffusion Models","created":"2026-05-04","cited_by_count":3,"area":"mllm"},{"id":"2402.15653","title":"Low-Frequency Black-Box Backdoor Attack via Evolutionary Algorithm","created":"2024-02-23","cited_by_count":2,"area":null},{"id":"2403.15010","title":"Clean-image Backdoor Attacks","created":"2024-03-22","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":"2411.19075","title":"LADDER: Multi-objective Backdoor Attack via Evolutionary Algorithm","created":"2024-11-28","cited_by_count":2,"area":null},{"id":"2502.16545","title":"Multi-Target Federated Backdoor Attack Based on Feature Aggregation","created":"2025-02-23","cited_by_count":2,"area":null},{"id":"2504.21054","title":"FFCBA: Feature-based Full-target Clean-label Backdoor Attacks","created":"2025-04-29","cited_by_count":2,"area":null},{"id":"2505.22829","title":"Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies","created":"2025-05-28","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":"2508.01074","title":"Evading Data Provenance in Deep Neural Networks","created":"2025-08-01","cited_by_count":2,"area":null},{"id":"2510.09210","title":"Provable Watermarking for Data Poisoning Attacks","created":"2025-10-10","cited_by_count":2,"area":null},{"id":"2510.14299","title":"TED++: Submanifold-Aware Backdoor Detection via Layerwise Tubular-Neighbourhood Screening","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2212.09979","title":"Flareon: Stealthy any2any Backdoor Injection via Poisoned Augmentation","created":"2022-12-20","cited_by_count":1,"area":null},{"id":"2302.04977","title":"Mithridates: Auditing and Boosting Backdoor Resistance of Machine Learning Pipelines","created":"2023-02-09","cited_by_count":1,"area":null},{"id":"2306.16415","title":"On Practical Aspects of Aggregation Defenses against Data Poisoning Attacks","created":"2023-06-28","cited_by_count":1,"area":"safety"},{"id":"2406.19753","title":"Attack On Prompt: Backdoor Attack in Prompt-Based Continual Learning","created":"2024-06-28","cited_by_count":1,"area":"safety"},{"id":"2408.13221","title":"Protecting against simultaneous data poisoning attacks","created":"2024-08-23","cited_by_count":1,"area":"safety"},{"id":"2410.01128","title":"Using Interleaved Ensemble Unlearning to Keep Backdoors at Bay for Finetuning Vision Transformers","created":"2024-10-01","cited_by_count":1,"area":"safety"},{"id":"2410.11290","title":"Backdoor Attack on Vertical Federated Graph Neural Network Learning","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2411.14449","title":"Unlearn to Relearn Backdoors: Deferred Backdoor Functionality Attacks on Deep Learning Models","created":"2024-11-10","cited_by_count":1,"area":null},{"id":"2411.16763","title":"Hide in Plain Sight: Clean-Label Backdoor for Auditing Membership Inference","created":"2024-11-24","cited_by_count":1,"area":null},{"id":"2505.15308","title":"BadSR: Stealthy Label Backdoor Attacks on Image Super-Resolution","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2505.19821","title":"Poison in the Well: Feature Embedding Disruption in Backdoor Attacks","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2509.03179","title":"AutoDetect: Designing an Autoencoder-based Detection Method for Poisoning Attacks on Object Detection Applications in the Military Domain","created":"2025-09-03","cited_by_count":1,"area":null},{"id":"2509.25613","title":"SMS: Self-supervised Model Seeding for Verification of Machine Unlearning","created":"2025-09-30","cited_by_count":1,"area":"safety"},{"id":"2512.15769","title":"Data-Chain Backdoor: Do You Trust Diffusion Models as Generative Data Supplier?","created":"2025-12-12","cited_by_count":1,"area":"diffusion"},{"id":"2602.10780","title":"Kill it with FIRE: On Leveraging Latent Space Directions for Runtime Backdoor Mitigation in Deep Neural Networks","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2603.13864","title":"Inevitable Encounters: Backdoor Attacks Involving Lossy Compression","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2301.02615","title":"Silent Killer: A Stealthy, Clean-Label, Black-Box Backdoor Attack","created":"2023-01-05","cited_by_count":0,"area":null},{"id":"2308.09487","title":"DFB: A Data-Free, Low-Budget, and High-Efficacy Clean-Label Backdoor Attack","created":"2023-08-18","cited_by_count":0,"area":null},{"id":"2405.19376","title":"PureEBM: Universal Poison Purification via Mid-Run Dynamics of Energy-Based Models","created":"2024-05-28","cited_by_count":0,"area":"safety"},{"id":"2411.10673","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","created":"2024-11-16","cited_by_count":0,"area":null},{"id":"2412.13324","title":"BadSAD: Clean-Label Backdoor Attacks against Deep Semi-Supervised Anomaly Detection","created":"2024-12-17","cited_by_count":0,"area":null},{"id":"2508.05404","title":"NT-ML: Backdoor Defense via Non-target Label Training and Mutual Learning","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2509.11525","title":"DARD: Dice Adversarial Robustness Distillation against Adversarial Attacks","created":"2025-09-15","cited_by_count":0,"area":"distill"},{"id":"2509.25792","title":"PUREVQ-GAN: Defending Data Poisoning Attacks through Vector-Quantized Bottlenecks","created":"2025-09-30","cited_by_count":0,"area":"safety"},{"id":"2511.12046","title":"BackWeak: Backdooring Knowledge Distillation Simply with Weak Triggers and Fine-tuning","created":"2025-11-15","cited_by_count":0,"area":"distill"},{"id":"2512.06243","title":"Quantization Blindspots: How Model Compression Breaks Backdoor Defenses","created":"2025-12-06","cited_by_count":0,"area":null},{"id":"2512.10402","title":"The Eminence in Shadow: Exploiting Feature Boundary Ambiguity for Robust Backdoor Attacks","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2602.00183","title":"RPP: A Certified Poisoned-Sample Detection Framework for Backdoor Attacks under Dataset Imbalance","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.03316","title":"Invisible Clean-Label Backdoor Attacks for Generative Data Augmentation","created":"2026-02-03","cited_by_count":0,"area":"safety"},{"id":"2603.00711","title":"IU: Imperceptible Universal Backdoor Attack","created":"2026-02-28","cited_by_count":0,"area":null},{"id":"2604.20047","title":"PASTA: A Patch-Agnostic Twofold-Stealthy Backdoor Attack on Vision Transformers","created":"2026-04-21","cited_by_count":0,"area":"safety"},{"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":"2605.11592","title":"SoK: Unlearnability and Unlearning for Model Dememorization","created":"2026-05-12","cited_by_count":0,"area":"safety"},{"id":"2605.18908","title":"Fast and Lightweight Backdoor Detection via Head Random Probing","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2605.27689","title":"Test-Time Collective Action: Proxy-Based Perturbations for Correcting Algorithmic Harms","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2605.28597","title":"Position: Retire the \"Positive Backdoor\" Label -- Secret Alignment Requires Strict and Systematic Evaluation","created":"2026-05-27","cited_by_count":0,"area":"alignment"},{"id":"2606.11698","title":"T2S: A Rehearsal-Based Approach for Extraction-Resistant Model Watermarking","created":"2026-06-10","cited_by_count":0,"area":"safety"},{"id":"2606.20752","title":"Mirage: a Clean-Label Backdoor against LiDAR 3D Object Detection","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.06643","title":"The Power of Backdoor Absorption in Community Training","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.26099","title":"Lilith: Backdoor Generalization under Training-Inference Trigger Shift","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.00732","title":"Mitigating Backdoors via Decoy Shortcuts and Knowledge Decoupling","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2608.18095","title":"Backdoor Learning in Language Models and Vision-Language Models","created":"2026-06-08","cited_by_count":0,"area":"mllm"}],"next_cursor":"100"}