{"total":199,"rows":[{"id":"2308.03825","title":"\"Do Anything Now\": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models","created":"2023-08-07","cited_by_count":489,"area":"safety"},{"id":"2302.10149","title":"Poisoning Web-Scale Training Datasets is Practical","created":"2023-02-20","cited_by_count":290,"area":null},{"id":"2110.11571","title":"Anti-Backdoor Learning: Training Clean Models on Poisoned Data","created":"2021-10-22","cited_by_count":263,"area":null},{"id":"2110.03735","title":"Adversarial Unlearning of Backdoors via Implicit Hypergradient","created":"2021-10-07","cited_by_count":166,"area":null},{"id":"2104.03413","title":"Rethinking the Backdoor Attacks' Triggers: A Frequency Perspective","created":"2021-04-07","cited_by_count":161,"area":"safety"},{"id":"2202.03423","title":"Backdoor Defense via Decoupling the Training Process","created":"2022-02-05","cited_by_count":153,"area":null},{"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":"2102.05123","title":"Backdoor Scanning for Deep Neural Networks through K-Arm Optimization","created":"2021-02-09","cited_by_count":98,"area":null},{"id":"2402.05668","title":"JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs","created":"2024-02-08","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":"2105.00164","title":"Hidden Backdoors in Human-Centric Language Models","created":"2021-05-01","cited_by_count":90,"area":"safety"},{"id":"2106.06361","title":"Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution","created":"2021-06-11","cited_by_count":89,"area":"safety"},{"id":"2102.02551","title":"ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models","created":"2021-02-04","cited_by_count":85,"area":"safety"},{"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":"2111.07970","title":"Triggerless Backdoor Attack for NLP Tasks with Clean Labels","created":"2021-11-15","cited_by_count":66,"area":"safety"},{"id":"2106.04690","title":"Handcrafted Backdoors in Deep Neural Networks","created":"2021-06-08","cited_by_count":63,"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":"2301.02344","title":"TrojanPuzzle: Covertly Poisoning Code-Suggestion Models","created":"2023-01-06","cited_by_count":60,"area":null},{"id":"2305.14876","title":"Reconstructive Neuron Pruning for Backdoor Defense","created":"2023-05-24","cited_by_count":59,"area":null},{"id":"2212.14315","title":"\"Real Attackers Don't Compute Gradients\": Bridging the Gap Between Adversarial ML Research and Practice","created":"2022-12-29","cited_by_count":56,"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":"2303.15180","title":"Detecting Backdoors in Pre-trained Encoders","created":"2023-03-23","cited_by_count":55,"area":"safety"},{"id":"2205.12700","title":"BITE: Textual Backdoor Attacks with Iterative Trigger Injection","created":"2022-05-25","cited_by_count":53,"area":"safety"},{"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":"2301.02496","title":"Stealthy Backdoor Attack for Code Models","created":"2023-01-06","cited_by_count":49,"area":"safety"},{"id":"2202.05749","title":"Constrained Optimization with Dynamic Bound-scaling for Effective NLPBackdoor Defense","created":"2022-02-11","cited_by_count":47,"area":"safety"},{"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":"2304.02786","title":"UNICORN: A Unified Backdoor Trigger Inversion Framework","created":"2023-04-05","cited_by_count":46,"area":null},{"id":"2107.14569","title":"Can You Hear It? Backdoor Attacks via Ultrasonic Triggers","created":"2021-07-30","cited_by_count":44,"area":null},{"id":"2109.06024","title":"Formalizing and Estimating Distribution Inference Risks","created":"2021-09-13","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":"2205.13616","title":"Towards A Proactive ML Approach for Detecting Backdoor Poison Samples","created":"2022-05-26","cited_by_count":40,"area":null},{"id":"2210.15127","title":"Rethinking the Reverse-engineering of Trojan Triggers","created":"2022-10-27","cited_by_count":39,"area":"safety"},{"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":"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":"2212.09067","title":"Fine-Tuning Is All You Need to Mitigate Backdoor Attacks","created":"2022-12-18","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":"2111.12965","title":"Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks","created":"2021-11-25","cited_by_count":34,"area":null},{"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":"2210.07346","title":"An Embarrassingly Simple Backdoor Attack on Self-supervised Learning","created":"2022-10-13","cited_by_count":31,"area":null},{"id":"2312.00050","title":"Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift","created":"2023-11-27","cited_by_count":31,"area":"diffusion"},{"id":"2108.09187","title":"Quantization Backdoors to Deep Learning Commercial Frameworks","created":"2021-08-20","cited_by_count":29,"area":null},{"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":"2211.08229","title":"CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning","created":"2022-11-15","cited_by_count":29,"area":"safety"},{"id":"2207.04497","title":"One-shot Neural Backdoor Erasing via Adversarial Weight Masking","created":"2022-07-10","cited_by_count":28,"area":null},{"id":"2110.11024","title":"Watermarking Graph Neural Networks based on Backdoor Attacks","created":"2021-10-21","cited_by_count":25,"area":null},{"id":"2402.14845","title":"Purifying Large Language Models by Ensembling a Small Language Model","created":"2024-02-19","cited_by_count":25,"area":"safety"},{"id":"2102.13624","title":"What Doesn't Kill You Makes You Robust(er): How to Adversarially Train against Data Poisoning","created":"2021-02-26","cited_by_count":22,"area":"safety"},{"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":"2307.00682","title":"Tools for Verifying Neural Models' Training Data","created":"2023-07-02","cited_by_count":22,"area":null},{"id":"2107.07240","title":"Subnet Replacement: Deployment-stage backdoor attack against deep neural networks in gray-box setting","created":"2021-07-15","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":"2106.07798","title":"Poisoning Deep Reinforcement Learning Agents with In-Distribution Triggers","created":"2021-06-14","cited_by_count":20,"area":"safety"},{"id":"2301.10908","title":"Distilling Cognitive Backdoor Patterns within an Image","created":"2023-01-26","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":"2210.07907","title":"Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks","created":"2022-10-14","cited_by_count":19,"area":"safety"},{"id":"2308.02122","title":"ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLP","created":"2023-08-04","cited_by_count":19,"area":"safety"},{"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":"2104.15129","title":"Stealthy Backdoors as Compression Artifacts","created":"2021-04-30","cited_by_count":18,"area":null},{"id":"2305.18651","title":"UMD: Unsupervised Model Detection for X2X Backdoor Attacks","created":"2023-05-29","cited_by_count":18,"area":null},{"id":"2405.12725","title":"Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks","created":"2024-05-21","cited_by_count":18,"area":null},{"id":"2202.07183","title":"A Survey of Neural Trojan Attacks and Defenses in Deep Learning","created":"2022-02-15","cited_by_count":17,"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":"2209.05244","title":"Universal Backdoor Attacks Detection via Adaptive Adversarial Probe","created":"2022-09-12","cited_by_count":16,"area":null},{"id":"2111.05077","title":"Enhancing Backdoor Attacks with Multi-Level MMD Regularization","created":"2021-11-09","cited_by_count":15,"area":null},{"id":"2212.07591","title":"Dissecting Distribution Inference","created":"2022-12-15","cited_by_count":15,"area":null},{"id":"2301.06241","title":"BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense","created":"2023-01-16","cited_by_count":15,"area":null},{"id":"2409.19993","title":"Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges","created":"2024-09-30","cited_by_count":15,"area":"safety"},{"id":"2202.05470","title":"Jigsaw Puzzle: Selective Backdoor Attack to Subvert Malware Classifiers","created":"2022-02-11","cited_by_count":14,"area":null},{"id":"2310.18603","title":"Large Language Models Are Better Adversaries: Exploring Generative Clean-Label Backdoor Attacks Against Text Classifiers","created":"2023-10-28","cited_by_count":14,"area":"safety"},{"id":"2312.08890","title":"Defenses in Adversarial Machine Learning: A Survey","created":"2023-12-13","cited_by_count":14,"area":null},{"id":"2402.01096","title":"Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance","created":"2024-02-02","cited_by_count":14,"area":null},{"id":"2402.01920","title":"Preference Poisoning Attacks on Reward Model Learning","created":"2024-02-02","cited_by_count":14,"area":"alignment"},{"id":"2503.15293","title":"Test-Time Backdoor Detection for Object Detection Models","created":"2025-03-19","cited_by_count":14,"area":null},{"id":"2310.17498","title":"CBD: A Certified Backdoor Detector Based on Local Dominant Probability","created":"2023-10-26","cited_by_count":13,"area":null},{"id":"2403.10717","title":"Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency","created":"2024-03-15","cited_by_count":13,"area":null},{"id":"2403.17188","title":"LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning","created":"2024-03-25","cited_by_count":13,"area":null},{"id":"2405.05466","title":"Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals","created":"2024-05-08","cited_by_count":13,"area":null},{"id":"2409.01193","title":"CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models","created":"2024-09-02","cited_by_count":13,"area":"safety"},{"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":"2210.10886","title":"Backdoor Attack and Defense in Federated Generative Adversarial Network-based Medical Image Synthesis","created":"2022-10-19","cited_by_count":12,"area":"safety"},{"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":"2308.12439","title":"BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection","created":"2023-08-23","cited_by_count":11,"area":null},{"id":"2406.07778","title":"A Study of Backdoors in Instruction Fine-tuned Language Models","created":"2024-06-12","cited_by_count":11,"area":"safety"},{"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":"2409.00399","title":"Rethinking Backdoor Detection Evaluation for Language Models","created":"2024-08-31","cited_by_count":9,"area":"lr"},{"id":"2303.11643","title":"Manipulating Transfer Learning for Property Inference","created":"2023-03-21","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":"2310.13424","title":"FLTracer: Accurate Poisoning Attack Provenance in Federated Learning","created":"2023-10-20","cited_by_count":8,"area":null},{"id":"2208.08662","title":"Private, Efficient, and Accurate: Protecting Models Trained by Multi-party Learning with Differential Privacy","created":"2022-08-18","cited_by_count":7,"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":"2302.14500","title":"FreeEagle: Detecting Complex Neural Trojans in Data-Free Cases","created":"2023-02-28","cited_by_count":7,"area":"safety"},{"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":"2412.06219","title":"Data Free Backdoor Attacks","created":"2024-12-09","cited_by_count":7,"area":null},{"id":"2105.14259","title":"Detecting Backdoor in Deep Neural Networks via Intentional Adversarial Perturbations","created":"2021-05-29","cited_by_count":6,"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}],"next_cursor":"100"}