{"total":426,"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":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2110.01167","title":"Trustworthy AI: From Principles to Practices","created":"2021-10-04","cited_by_count":207,"area":null},{"id":"2202.03423","title":"Backdoor Defense via Decoupling the Training Process","created":"2022-02-05","cited_by_count":153,"area":null},{"id":"2212.04612","title":"Training Data Influence Analysis and Estimation: A Survey","created":"2022-12-09","cited_by_count":135,"area":null},{"id":"2206.12654","title":"BackdoorBench: A Comprehensive Benchmark of Backdoor Learning","created":"2022-06-25","cited_by_count":128,"area":null},{"id":"2305.14710","title":"Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models","created":"2023-05-24","cited_by_count":110,"area":"safety"},{"id":"2204.05255","title":"Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information","created":"2022-04-11","cited_by_count":103,"area":null},{"id":"2106.08970","title":"Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch","created":"2021-06-16","cited_by_count":102,"area":"safety"},{"id":"2102.05123","title":"Backdoor Scanning for Deep Neural Networks through K-Arm Optimization","created":"2021-02-09","cited_by_count":98,"area":null},{"id":"2205.01992","title":"Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning","created":"2022-05-04","cited_by_count":94,"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":"2210.00875","title":"Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection","created":"2022-09-27","cited_by_count":86,"area":null},{"id":"2110.02467","title":"BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models","created":"2021-10-06","cited_by_count":85,"area":"safety"},{"id":"2201.06640","title":"Towards Adversarial Evaluations for Inexact Machine Unlearning","created":"2022-01-17","cited_by_count":84,"area":"safety"},{"id":"2401.12242","title":"BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models","created":"2024-01-20","cited_by_count":80,"area":"lr"},{"id":"2406.20053","title":"Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation","created":"2024-06-28","cited_by_count":80,"area":null},{"id":"2208.03111","title":"Data-free Backdoor Removal based on Channel Lipschitzness","created":"2022-08-05","cited_by_count":79,"area":null},{"id":"2206.08514","title":"A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks","created":"2022-06-17","cited_by_count":74,"area":"safety"},{"id":"2112.05224","title":"Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasures","created":"2021-12-09","cited_by_count":73,"area":"safety"},{"id":"2407.01599","title":"JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models","created":"2024-06-26","cited_by_count":70,"area":"mllm"},{"id":"2104.14362","title":"From Distributed Machine Learning to Federated Learning: A Survey","created":"2021-04-29","cited_by_count":66,"area":null},{"id":"2209.06015","title":"Black-box Dataset Ownership Verification via Backdoor Watermarking","created":"2022-08-04","cited_by_count":65,"area":null},{"id":"2303.03323","title":"CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning","created":"2023-03-06","cited_by_count":63,"area":"safety"},{"id":"2310.20448","title":"A Survey on Federated Unlearning: Challenges, Methods, and Future Directions","created":"2023-10-31","cited_by_count":63,"area":"safety"},{"id":"2402.09179","title":"Instruction Backdoor Attacks Against Customized LLMs","created":"2024-02-14","cited_by_count":62,"area":"safety"},{"id":"2112.01148","title":"FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysis","created":"2021-12-02","cited_by_count":61,"area":null},{"id":"2310.14942","title":"Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand","created":"2023-10-09","cited_by_count":57,"area":null},{"id":"2205.06900","title":"MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic","created":"2022-05-13","cited_by_count":55,"area":null},{"id":"2105.00203","title":"Adversarial Example Detection for DNN Models: A Review and Experimental Comparison","created":"2021-05-01","cited_by_count":52,"area":null},{"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":"2108.02488","title":"Poison Ink: Robust and Invisible Backdoor Attack","created":"2021-08-05","cited_by_count":50,"area":null},{"id":"2101.06969","title":"Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-Level Backdoor Attacks","created":"2021-01-18","cited_by_count":49,"area":null},{"id":"2411.02306","title":"On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback","created":"2024-11-04","cited_by_count":47,"area":"alignment"},{"id":"2112.03476","title":"Defending against Model Stealing via Verifying Embedded External Features","created":"2021-12-07","cited_by_count":46,"area":null},{"id":"2303.18191","title":"Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency","created":"2023-03-27","cited_by_count":46,"area":null},{"id":"2405.19550","title":"Stress-Testing Capability Elicitation With Password-Locked Models","created":"2024-05-29","cited_by_count":46,"area":null},{"id":"2407.14937","title":"Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)","created":"2024-07-20","cited_by_count":46,"area":"safety"},{"id":"2303.12175","title":"Black-box Backdoor Defense via Zero-shot Image Purification","created":"2023-03-21","cited_by_count":45,"area":null},{"id":"2303.12993","title":"Backdoor Defense via Adaptively Splitting Poisoned Dataset","created":"2023-03-23","cited_by_count":43,"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":"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":"2112.14889","title":"Few-shot Backdoor Defense Using Shapley Estimation","created":"2021-12-30","cited_by_count":41,"area":null},{"id":"2205.13616","title":"Towards A Proactive ML Approach for Detecting Backdoor Poison Samples","created":"2022-05-26","cited_by_count":40,"area":null},{"id":"2302.14677","title":"Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger","created":"2023-02-28","cited_by_count":40,"area":null},{"id":"2402.08577","title":"Test-Time Backdoor Attacks on Multimodal Large Language Models","created":"2024-02-13","cited_by_count":40,"area":"mllm"},{"id":"2405.04825","title":"Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution","created":"2024-05-08","cited_by_count":40,"area":"safety"},{"id":"2403.13682","title":"Threats, Attacks, and Defenses in Machine Unlearning: A Survey","created":"2024-03-20","cited_by_count":39,"area":"safety"},{"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":"2409.19232","title":"TrojVLM: Backdoor Attack Against Vision Language Models","created":"2024-09-28","cited_by_count":39,"area":"mllm"},{"id":"2505.16640","title":"BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization","created":"2025-05-22","cited_by_count":38,"area":"vla"},{"id":"2112.07668","title":"Dual-Key Multimodal Backdoors for Visual Question Answering","created":"2021-12-14","cited_by_count":37,"area":"safety"},{"id":"2303.11470","title":"Did You Train on My Dataset? Towards Public Dataset Protection with Clean-Label Backdoor Watermarking","created":"2023-03-20","cited_by_count":37,"area":null},{"id":"2201.13178","title":"Few-Shot Backdoor Attacks on Visual Object Tracking","created":"2022-01-31","cited_by_count":35,"area":null},{"id":"2410.10760","title":"Denial-of-Service Poisoning Attacks against Large Language Models","created":"2024-10-14","cited_by_count":35,"area":null},{"id":"2505.16916","title":"Backdoor Cleaning without External Guidance in MLLM Fine-tuning","created":"2025-05-22","cited_by_count":35,"area":"mllm"},{"id":"2505.11154","title":"MPMA: Preference Manipulation Attack Against Model Context Protocol","created":"2025-05-16","cited_by_count":34,"area":"agents"},{"id":"2303.02213","title":"Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directions","created":"2023-03-03","cited_by_count":33,"area":null},{"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":"2410.01264","title":"Backdooring Vision-Language Models with Out-Of-Distribution Data","created":"2024-10-02","cited_by_count":33,"area":"mllm"},{"id":"2201.10055","title":"Identifying a Training-Set Attack's Target Using Renormalized Influence Estimation","created":"2022-01-25","cited_by_count":32,"area":null},{"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":"2203.00858","title":"Physical Backdoor Attacks to Lane Detection Systems in Autonomous Driving","created":"2022-03-02","cited_by_count":31,"area":null},{"id":"2302.04116","title":"Training-free Lexical Backdoor Attacks on Language Models","created":"2023-02-08","cited_by_count":31,"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":"2211.07160","title":"FedTracker: Furnishing Ownership Verification and Traceability for Federated Learning Model","created":"2022-11-14","cited_by_count":30,"area":"safety"},{"id":"2303.15127","title":"Learning the Unlearnable: Adversarial Augmentations Suppress Unlearnable Example Attacks","created":"2023-03-27","cited_by_count":30,"area":"safety"},{"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":"2201.08474","title":"Post-Training Detection of Backdoor Attacks for Two-Class and Multi-Attack Scenarios","created":"2022-01-20","cited_by_count":29,"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":"2310.18933","title":"Label Poisoning is All You Need","created":"2023-10-29","cited_by_count":29,"area":"safety"},{"id":"2210.15198","title":"Watermarking for Out-of-distribution Detection","created":"2022-10-27","cited_by_count":28,"area":null},{"id":"2211.05638","title":"Untargeted Backdoor Attack against Object Detection","created":"2022-11-02","cited_by_count":28,"area":null},{"id":"2604.09378","title":"BadSkill: Backdoor Attacks on Agent Skills via Model-in-Skill Poisoning","created":"2026-04-10","cited_by_count":27,"area":"safety"},{"id":"2302.01762","title":"BackdoorBox: A Python Toolbox for Backdoor Learning","created":"2023-02-01","cited_by_count":26,"area":null},{"id":"2405.05553","title":"Towards Robust Physical-world Backdoor Attacks on Lane Detection","created":"2024-05-09","cited_by_count":26,"area":null},{"id":"2502.05673","title":"The Evolution of Dataset Distillation: Toward Scalable and Generalizable Solutions","created":"2025-02-08","cited_by_count":26,"area":null},{"id":"2208.08052","title":"Imperceptible and Robust Backdoor Attack in 3D Point Cloud","created":"2022-08-17","cited_by_count":25,"area":null},{"id":"2212.09360","title":"AI Security for Geoscience and Remote Sensing: Challenges and Future Trends","created":"2022-12-19","cited_by_count":23,"area":null},{"id":"2302.12461","title":"Analyzing And Editing Inner Mechanisms Of Backdoored Language Models","created":"2023-02-24","cited_by_count":23,"area":"safety"},{"id":"2405.09981","title":"Adversarial Robustness for Visual Grounding of Multimodal Large Language Models","created":"2024-05-16","cited_by_count":23,"area":"mllm"},{"id":"2207.13417","title":"Hardly Perceptible Trojan Attack against Neural Networks with Bit Flips","created":"2022-07-27","cited_by_count":22,"area":null},{"id":"2502.18508","title":"REFINE: Inversion-Free Backdoor Defense via Model Reprogramming","created":"2025-02-22","cited_by_count":22,"area":null},{"id":"2509.11864","title":"NeuroStrike: Neuron-Level Attacks on Aligned LLMs","created":"2025-09-15","cited_by_count":22,"area":"alignment"},{"id":"2208.02820","title":"MOVE: Effective and Harmless Ownership Verification via Embedded External Features","created":"2022-08-04","cited_by_count":21,"area":null},{"id":"2301.01197","title":"Backdoor Attacks Against Dataset Distillation","created":"2023-01-03","cited_by_count":21,"area":null},{"id":"2207.10825","title":"Just Rotate it: Deploying Backdoor Attacks via Rotation Transformation","created":"2022-07-22","cited_by_count":20,"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":"2306.06209","title":"Backdoor Attack with Sparse and Invisible Trigger","created":"2023-05-11","cited_by_count":20,"area":null},{"id":"2408.05500","title":"PointNCBW: Towards Dataset Ownership Verification for Point Clouds via Negative Clean-label Backdoor Watermark","created":"2024-08-10","cited_by_count":20,"area":null},{"id":"2202.03609","title":"PolicyCleanse: Backdoor Detection and Mitigation in Reinforcement Learning","created":"2022-02-08","cited_by_count":19,"area":null},{"id":"2207.00425","title":"Transferable Graph Backdoor Attack","created":"2022-06-21","cited_by_count":19,"area":null},{"id":"2310.18633","title":"Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots","created":"2023-10-28","cited_by_count":19,"area":"safety"},{"id":"2401.15295","title":"Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks","created":"2024-01-27","cited_by_count":19,"area":null},{"id":"2506.07596","title":"TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts","created":"2025-06-09","cited_by_count":19,"area":"safety"},{"id":"2506.16447","title":"Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models","created":"2025-06-19","cited_by_count":19,"area":"alignment"},{"id":"2110.08247","title":"Textual Backdoor Attacks Can Be More Harmful via Two Simple Tricks","created":"2021-10-15","cited_by_count":18,"area":"safety"},{"id":"2305.18651","title":"UMD: Unsupervised Model Detection for X2X Backdoor Attacks","created":"2023-05-29","cited_by_count":18,"area":null},{"id":"2312.08667","title":"Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Survey","created":"2023-12-14","cited_by_count":18,"area":null},{"id":"2507.03034","title":"Rethinking Data Protection in the (Generative) Artificial Intelligence Era","created":"2025-07-03","cited_by_count":18,"area":null}],"next_cursor":"100"}