{"total":123,"rows":[{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2206.12654","title":"BackdoorBench: A Comprehensive Benchmark of Backdoor Learning","created":"2022-06-25","cited_by_count":128,"area":null},{"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":"2406.03007","title":"BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents","created":"2024-06-05","cited_by_count":115,"area":"agents"},{"id":"2411.00348","title":"Attention Tracker: Detecting Prompt Injection Attacks in LLMs","created":"2024-11-01","cited_by_count":95,"area":"safety"},{"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":"2111.00197","title":"Backdoor Pre-trained Models Can Transfer to All","created":"2021-10-30","cited_by_count":86,"area":null},{"id":"2104.02361","title":"Backdoor Attack in the Physical World","created":"2021-04-06","cited_by_count":84,"area":null},{"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":"2209.15179","title":"Physical Adversarial Attack meets Computer Vision: A Decade Survey","created":"2022-09-30","cited_by_count":67,"area":null},{"id":"2304.11823","title":"Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization","created":"2023-04-24","cited_by_count":64,"area":null},{"id":"2209.11715","title":"The \"Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matrices","created":"2022-09-23","cited_by_count":63,"area":null},{"id":"2108.02488","title":"Poison Ink: Robust and Invisible Backdoor Attack","created":"2021-08-05","cited_by_count":50,"area":null},{"id":"2108.12204","title":"This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagation","created":"2021-08-27","cited_by_count":43,"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":"2309.06055","title":"Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review","created":"2023-09-12","cited_by_count":39,"area":"safety"},{"id":"2210.08151","title":"ProtoVAE: A Trustworthy Self-Explainable Prototypical Variational Model","created":"2022-10-15","cited_by_count":34,"area":null},{"id":"2108.09187","title":"Quantization Backdoors to Deep Learning Commercial Frameworks","created":"2021-08-20","cited_by_count":29,"area":null},{"id":"2210.07714","title":"CrowdGuard: Federated Backdoor Detection in Federated Learning","created":"2022-10-14","cited_by_count":27,"area":null},{"id":"2302.01762","title":"BackdoorBox: A Python Toolbox for Backdoor Learning","created":"2023-02-01","cited_by_count":26,"area":null},{"id":"2502.12575","title":"DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent","created":"2025-02-18","cited_by_count":23,"area":"agents"},{"id":"2201.08619","title":"Dangerous Cloaking: Natural Trigger based Backdoor Attacks on Object Detectors in the Physical World","created":"2022-01-21","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":"2302.09457","title":"Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective","created":"2023-02-19","cited_by_count":20,"area":null},{"id":"2502.12176","title":"Ten Challenging Problems in Federated Foundation Models","created":"2025-02-14","cited_by_count":20,"area":"safety"},{"id":"2207.00425","title":"Transferable Graph Backdoor Attack","created":"2022-06-21","cited_by_count":19,"area":null},{"id":"2407.19845","title":"BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning","created":"2024-07-29","cited_by_count":19,"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":"2505.06413","title":"Natural Reflection Backdoor Attack on Vision Language Model for Autonomous Driving","created":"2025-05-09","cited_by_count":18,"area":"lr"},{"id":"2205.02589","title":"A Temporal-Pattern Backdoor Attack to Deep Reinforcement Learning","created":"2022-05-05","cited_by_count":16,"area":null},{"id":"2503.11832","title":"Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning","created":"2025-03-14","cited_by_count":16,"area":"mllm"},{"id":"2312.08890","title":"Defenses in Adversarial Machine Learning: A Survey","created":"2023-12-13","cited_by_count":14,"area":null},{"id":"2103.10274","title":"TOP: Backdoor Detection in Neural Networks via Transferability of Perturbation","created":"2021-03-18","cited_by_count":13,"area":null},{"id":"2211.15929","title":"Backdoor Vulnerabilities in Normally Trained Deep Learning Models","created":"2022-11-29","cited_by_count":13,"area":null},{"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":"2406.15213","title":"Backdooring Bias ($B^2$) into Stable Diffusion Models","created":"2024-06-21","cited_by_count":12,"area":"diffusion"},{"id":"2204.06273","title":"Towards A Critical Evaluation of Robustness for Deep Learning Backdoor Countermeasures","created":"2022-04-13","cited_by_count":11,"area":null},{"id":"2212.04687","title":"Selective Amnesia: On Efficient, High-Fidelity and Blind Suppression of Backdoor Effects in Trojaned Machine Learning Models","created":"2022-12-09","cited_by_count":11,"area":null},{"id":"2506.05401","title":"Robust Anti-Backdoor Instruction Tuning in LVLMs","created":"2025-06-04","cited_by_count":11,"area":"mllm"},{"id":"2501.15509","title":"FIT-Print: Towards False-claim-resistant Model Ownership Verification via Targeted Fingerprint","created":"2025-01-26","cited_by_count":10,"area":null},{"id":"2103.05354","title":"Revisiting Model's Uncertainty and Confidences for Adversarial Example Detection","created":"2021-03-09","cited_by_count":9,"area":null},{"id":"2109.05507","title":"Check Your Other Door! Creating Backdoor Attacks in the Frequency Domain","created":"2021-09-12","cited_by_count":9,"area":null},{"id":"2207.00091","title":"Threat Assessment in Machine Learning based Systems","created":"2022-06-30","cited_by_count":9,"area":null},{"id":"2106.01425","title":"GAL: Gradient Assisted Learning for Decentralized Multi-Organization Collaborations","created":"2021-06-02","cited_by_count":8,"area":null},{"id":"2209.02339","title":"TransCAB: Transferable Clean-Annotation Backdoor to Object Detection with Natural Trigger in Real-World","created":"2022-09-06","cited_by_count":8,"area":null},{"id":"2302.01550","title":"Vertical Federated Learning: Taxonomies, Threats, and Prospects","created":"2023-02-03","cited_by_count":8,"area":null},{"id":"2310.00542","title":"Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade Defense","created":"2023-10-01","cited_by_count":8,"area":null},{"id":"2508.02175","title":"Hidden in the Noise: Unveiling Backdoors in Audio LLMs Alignment through Latent Acoustic Pattern Triggers","created":"2025-08-04","cited_by_count":8,"area":"safety"},{"id":"2105.04839","title":"Poisoning MorphNet for Clean-Label Backdoor Attack to Point Clouds","created":"2021-05-11","cited_by_count":7,"area":null},{"id":"2302.14500","title":"FreeEagle: Detecting Complex Neural Trojans in Data-Free Cases","created":"2023-02-28","cited_by_count":7,"area":"safety"},{"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":"2312.04902","title":"BELT: Old-School Backdoor Attacks can Evade the State-of-the-Art Defense with Backdoor Exclusivity Lifting","created":"2023-12-08","cited_by_count":7,"area":null},{"id":"2411.19479","title":"FLARE: Toward Universal Dataset Purification against Backdoor Attacks","created":"2024-11-29","cited_by_count":7,"area":null},{"id":"2509.11173","title":"Your Compiler is Backdooring Your Model: Understanding and Exploiting Compilation Inconsistency Vulnerabilities in Deep Learning Compilers","created":"2025-09-14","cited_by_count":7,"area":null},{"id":"2302.01740","title":"SoK: A Systematic Evaluation of Backdoor Trigger Characteristics in Image Classification","created":"2023-02-03","cited_by_count":6,"area":null},{"id":"2308.04406","title":"XGBD: Explanation-Guided Graph Backdoor Detection","created":"2023-08-08","cited_by_count":6,"area":null},{"id":"2311.11796","title":"Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systems","created":"2023-11-20","cited_by_count":6,"area":"safety"},{"id":"2312.07822","title":"Prototypical Self-Explainable Models Without Re-training","created":"2023-12-13","cited_by_count":6,"area":null},{"id":"2411.16154","title":"DeDe: Detecting Backdoor Samples for SSL Encoders via Decoders","created":"2024-11-25","cited_by_count":6,"area":"safety"},{"id":"2503.09956","title":"DeepSeek-Inspired Exploration of RL-based LLMs and Synergy with Wireless Networks: A Survey","created":"2025-03-13","cited_by_count":6,"area":null},{"id":"2103.08820","title":"EX-RAY: Distinguishing Injected Backdoor from Natural Features in Neural Networks by Examining Differential Feature Symmetry","created":"2021-03-16","cited_by_count":5,"area":null},{"id":"2106.07214","title":"Backdoor Learning Curves: Explaining Backdoor Poisoning Beyond Influence Functions","created":"2021-06-14","cited_by_count":5,"area":null},{"id":"2107.10443","title":"Spinning Sequence-to-Sequence Models with Meta-Backdoors","created":"2021-07-22","cited_by_count":5,"area":null},{"id":"2206.00145","title":"CASSOCK: Viable Backdoor Attacks against DNN in The Wall of Source-Specific Backdoor Defences","created":"2022-05-31","cited_by_count":5,"area":null},{"id":"2212.00322","title":"Hijack Vertical Federated Learning Models As One Party","created":"2022-12-01","cited_by_count":5,"area":null},{"id":"2406.10932","title":"Imperceptible Rhythm Backdoor Attacks: Exploring Rhythm Transformation for Embedding Undetectable Vulnerabilities on Speech Recognition","created":"2024-06-16","cited_by_count":5,"area":"safety"},{"id":"2412.11471","title":"TrapFlow: Controllable Website Fingerprinting Defense via Dynamic Backdoor Learning","created":"2024-12-16","cited_by_count":5,"area":null},{"id":"2503.04963","title":"Energy-Latency Attacks: A New Adversarial Threat to Deep Learning","created":"2025-03-06","cited_by_count":5,"area":null},{"id":"2503.23536","title":"A Survey on Unlearnable Data","created":"2025-03-30","cited_by_count":5,"area":null},{"id":"2509.23871","title":"Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack","created":"2025-09-28","cited_by_count":5,"area":"distill"},{"id":"2201.12211","title":"Backdoors Stuck At The Frontdoor: Multi-Agent Backdoor Attacks That Backfire","created":"2022-01-28","cited_by_count":4,"area":"safety"},{"id":"2203.03692","title":"Low-Loss Subspace Compression for Clean Gains against Multi-Agent Backdoor Attacks","created":"2022-03-07","cited_by_count":4,"area":"safety"},{"id":"2206.11981","title":"Never trust, always verify : a roadmap for Trustworthy AI?","created":"2022-06-23","cited_by_count":4,"area":null},{"id":"2301.03118","title":"Facial Misrecognition Systems: Simple Weight Manipulations Force DNNs to Err Only on Specific Persons","created":"2023-01-08","cited_by_count":4,"area":"safety"},{"id":"2302.06801","title":"Backdoor Learning for NLP: Recent Advances, Challenges, and Future Research Directions","created":"2023-02-14","cited_by_count":4,"area":"safety"},{"id":"2408.06063","title":"TruVRF: Towards Triple-Granularity Verification on Machine Unlearning","created":"2024-08-12","cited_by_count":4,"area":"safety"},{"id":"2105.03822","title":"RBNN: Memory-Efficient Reconfigurable Deep Binary Neural Network with IP Protection for Internet of Things","created":"2021-05-09","cited_by_count":3,"area":null},{"id":"2110.04571","title":"Widen The Backdoor To Let More Attackers In","created":"2021-10-09","cited_by_count":3,"area":null},{"id":"2111.11157","title":"NTD: Non-Transferability Enabled Backdoor Detection","created":"2021-11-22","cited_by_count":3,"area":null},{"id":"2211.14440","title":"Don't Watch Me: A Spatio-Temporal Trojan Attack on Deep-Reinforcement-Learning-Augment Autonomous Driving","created":"2022-11-22","cited_by_count":3,"area":"driving"},{"id":"2311.09428","title":"Beyond Detection: Unveiling Fairness Vulnerabilities in Abusive Language Models","created":"2023-11-15","cited_by_count":3,"area":null},{"id":"2401.01537","title":"The Art of Deception: Robust Backdoor Attack using Dynamic Stacking of Triggers","created":"2024-01-03","cited_by_count":3,"area":null},{"id":"2407.14738","title":"Flatness-aware Sequential Learning Generates Resilient Backdoors","created":"2024-07-20","cited_by_count":3,"area":"safety"},{"id":"2108.10132","title":"TRAPDOOR: Repurposing backdoors to detect dataset bias in machine learning-based genomic analysis","created":"2021-08-14","cited_by_count":2,"area":null},{"id":"2206.04677","title":"On the Permanence of Backdoors in Evolving Models","created":"2022-06-08","cited_by_count":2,"area":null},{"id":"2211.13535","title":"DeepTaster: Adversarial Perturbation-Based Fingerprinting to Identify Proprietary Dataset Use in Deep Neural Networks","created":"2022-11-24","cited_by_count":2,"area":"safety"},{"id":"2306.05494","title":"Evasion Adversarial Attacks Remain Impractical Against ML-based Network Intrusion Detection Systems, Especially Dynamic Ones","created":"2023-06-08","cited_by_count":2,"area":null},{"id":"2405.02828","title":"Trojans in Large Language Models of Code: A Critical Review through a Trigger-Based Taxonomy","created":"2024-05-05","cited_by_count":2,"area":null},{"id":"2406.03684","title":"Principles of Designing Robust Remote Face Anti-Spoofing Systems","created":"2024-06-06","cited_by_count":2,"area":null},{"id":"2409.02485","title":"Adversarial Attacks on Machine Learning-Aided Visualizations","created":"2024-09-04","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":"2512.23132","title":"Multi-Agent Framework for Threat Mitigation and Resilience in AI-Based Systems","created":"2025-12-29","cited_by_count":2,"area":"agents"},{"id":"2109.10512","title":"Backdoor Attacks on Federated Learning with Lottery Ticket Hypothesis","created":"2021-09-22","cited_by_count":1,"area":null},{"id":"2210.06509","title":"Understanding Impacts of Task Similarity on Backdoor Attack and Detection","created":"2022-10-12","cited_by_count":1,"area":null},{"id":"2306.03600","title":"Avoid Adversarial Adaption in Federated Learning by Multi-Metric Investigations","created":"2023-06-06","cited_by_count":1,"area":"safety"},{"id":"2402.08695","title":"Game of Trojans: Adaptive Adversaries Against Output-based Trojaned-Model Detectors","created":"2024-02-12","cited_by_count":1,"area":null},{"id":"2503.04853","title":"From Pixels to Trajectory: Universal Adversarial Example Detection via Temporal Imprints","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2503.20228","title":"TeleLoRA: Teleporting Model-Specific Alignment Across LLMs","created":"2025-03-26","cited_by_count":1,"area":null},{"id":"2504.00170","title":"Backdoor Detection through Replicated Execution of Outsourced Training","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2506.13205","title":"Poison Once, Control Anywhere: Clean-Text Visual Backdoors in VLM-based Mobile Agents","created":"2025-06-16","cited_by_count":1,"area":"mllm"}],"next_cursor":"100"}