{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/data-poisoning/papers/3","list_of":"/task/data-poisoning","task":"Data Poisoning","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":3,"pages_in_order":5,"rows_per_page":100,"rows":[201,300],"of":492,"counts":{"archive_papers_tagged":492,"with_a_code_link":170,"where_syntology_ran_a_sample":62,"not_listed_spam_title":0,"listed":492,"listed_where_code_ran":62,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":43,"every_run_a_failure_of_syntologys_instrument":19,"listed_with_a_run_with_no_instrument_failure":43,"listed_every_run_a_failure_of_syntologys_instrument":19,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/data-poisoning","prev":"/task/data-poisoning/papers/2","next":"/task/data-poisoning/papers/4","papers":[{"url":null,"slug":"optimizing-ml-training-with-metagradient","title":"Optimizing ML Training with Metagradient Descent","date":"2025-03-17","arxiv_id":"2503.13751","repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-teaching-via-data-poisoning-in","title":"Policy Teaching via Data Poisoning in Learning from Human Preferences","date":"2025-03-13","arxiv_id":"2503.10228","repositories_listed":0,"syntology":null},{"url":null,"slug":"targeted-data-poisoning-for-black-box-audio","title":"Targeted Data Poisoning for Black-Box Audio Datasets Ownership Verification","date":"2025-03-13","arxiv_id":"2503.10269","repositories_listed":0,"syntology":null},{"url":null,"slug":"silent-branding-attack-trigger-free-data","title":"Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models","date":"2025-03-12","arxiv_id":"2503.09669","repositories_listed":0,"syntology":null},{"url":null,"slug":"poisonedparrot-subtle-data-poisoning-attacks","title":"PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models","date":"2025-03-10","arxiv_id":"2503.07697","repositories_listed":0,"syntology":null},{"url":null,"slug":"poisoning-attacks-to-local-differential-1","title":"Poisoning Attacks to Local Differential Privacy Protocols for Trajectory Data","date":"2025-03-06","arxiv_id":"2503.07483","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-poisoning-attacks-to-locally-1","title":"Data Poisoning Attacks to Locally Differentially Private Range Query Protocols","date":"2025-03-05","arxiv_id":"2503.03454","repositories_listed":0,"syntology":null},{"url":null,"slug":"approaching-the-harm-of-gradient-attacks","title":"Approaching the Harm of Gradient Attacks While Only Flipping Labels","date":"2025-02-28","arxiv_id":"2503.00140","repositories_listed":0,"syntology":null},{"url":null,"slug":"atlas-a-framework-for-ml-lifecycle-provenance","title":"Atlas: A Framework for ML Lifecycle Provenance & Transparency","date":"2025-02-26","arxiv_id":"2502.19567","repositories_listed":0,"syntology":null},{"url":null,"slug":"no-of-course-i-can-refusal-mechanisms-can-be","title":"No, of course I can! Refusal Mechanisms Can Be Exploited Using Harmless Fine-Tuning Data","date":"2025-02-26","arxiv_id":"2502.19537","repositories_listed":0,"syntology":null},{"url":null,"slug":"fednia-noise-induced-activation-analysis-for","title":"FedNIA: Noise-Induced Activation Analysis for Mitigating Data Poisoning in FL","date":"2025-02-23","arxiv_id":"2502.16396","repositories_listed":0,"syntology":null},{"url":null,"slug":"swallowing-the-poison-pills-insights-from","title":"Swallowing the Poison Pills: Insights from Vulnerability Disparity Among LLMs","date":"2025-02-23","arxiv_id":"2502.18518","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-robust-attack-displacement-backdoor-attack","title":"A Robust Attack: Displacement Backdoor Attack","date":"2025-02-14","arxiv_id":"2502.10490","repositories_listed":0,"syntology":null},{"url":null,"slug":"detection-of-physiological-data-tampering","title":"Detection of Physiological Data Tampering Attacks with Quantum Machine Learning","date":"2025-02-09","arxiv_id":"2502.05966","repositories_listed":0,"syntology":null},{"url":null,"slug":"filter-obstruct-and-dilute-defending-against","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","date":"2025-02-09","arxiv_id":"2502.05755","repositories_listed":0,"syntology":null},{"url":null,"slug":"trojantime-backdoor-attacks-on-time-series","title":"TrojanTime: Backdoor Attacks on Time Series Classification","date":"2025-02-02","arxiv_id":"2502.00646","repositories_listed":0,"syntology":null},{"url":null,"slug":"provably-effective-detection-of-effective","title":"Provably effective detection of effective data poisoning attacks","date":"2025-01-21","arxiv_id":"2501.11795","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-pearson-correlation-based-merging","title":"A Novel Pearson Correlation-Based Merging Algorithm for Robust Distributed Machine Learning with Heterogeneous Data","date":"2025-01-19","arxiv_id":"2501.11112","repositories_listed":0,"syntology":null},{"url":null,"slug":"fortifying-federated-learning-towards","title":"Fortifying Federated Learning Towards Trustworthiness via Auditable Data Valuation and Verifiable Client Contribution","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"attacks-on-the-neural-network-and-defense","title":"Attacks on the neural network and defense methods","date":"2024-12-29","arxiv_id":"2412.20529","repositories_listed":0,"syntology":null},{"url":null,"slug":"cut-the-deadwood-out-post-training-model","title":"Cut the Deadwood Out: Post-Training Model Purification with Selective Module Substitution","date":"2024-12-29","arxiv_id":"2412.20476","repositories_listed":0,"syntology":null},{"url":null,"slug":"trading-devil-rl-backdoor-attack-via-stock","title":"Trading Devil RL: Backdoor attack via Stock market, Bayesian Optimization and Reinforcement Learning","date":"2024-12-23","arxiv_id":"2412.17908","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-and-code-security-a","title":"From Vulnerabilities to Remediation: A Systematic Literature Review of LLMs in Code Security","date":"2024-12-19","arxiv_id":"2412.15004","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-pixel-is-all-i-need","title":"One Pixel is All I Need","date":"2024-12-14","arxiv_id":"2412.10681","repositories_listed":0,"syntology":null},{"url":null,"slug":"bicert-a-bilinear-mixed-integer-programming","title":"BiCert: A Bilinear Mixed Integer Programming Formulation for Precise Certified Bounds Against Data Poisoning Attacks","date":"2024-12-13","arxiv_id":"2412.10186","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-model-security-threats-and","title":"Deep Learning Model Security: Threats and Defenses","date":"2024-12-12","arxiv_id":"2412.08969","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-forget-using-hypernetworks","title":"Learning to Forget using Hypernetworks","date":"2024-12-01","arxiv_id":"2412.00761","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-and-private-memorisation-under","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","date":"2024-11-24","arxiv_id":"2411.15831","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-poisoning-attack-on-quantum","title":"Adversarial Data Poisoning Attacks on Quantum Machine Learning in the NISQ Era","date":"2024-11-21","arxiv_id":"2411.14412","repositories_listed":0,"syntology":null},{"url":null,"slug":"reliable-poisoned-sample-detection-against","title":"Reliable Poisoned Sample Detection against Backdoor Attacks Enhanced by Sharpness Aware Minimization","date":"2024-11-18","arxiv_id":"2411.11525","repositories_listed":0,"syntology":null},{"url":null,"slug":"safeloc-overcoming-data-poisoning-attacks-in","title":"SAFELOC: Overcoming Data Poisoning Attacks in Heterogeneous Federated Machine Learning for Indoor Localization","date":"2024-11-13","arxiv_id":"2411.09055","repositories_listed":0,"syntology":null},{"url":null,"slug":"oml-open-monetizable-and-loyal-ai","title":"Reclaiming \"Open AI\" -- AI Model Serving Can Be Open Access, Yet Monetizable and Loyal","date":"2024-11-01","arxiv_id":"2411.03887","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-and-unlearning-of-fabricated","title":"Learning and Unlearning of Fabricated Knowledge in Language Models","date":"2024-10-29","arxiv_id":"2410.21750","repositories_listed":0,"syntology":null},{"url":null,"slug":"inverting-gradient-attacks-naturally-makes","title":"Inverting Gradient Attacks Makes Powerful Data Poisoning","date":"2024-10-28","arxiv_id":"2410.21453","repositories_listed":0,"syntology":null},{"url":null,"slug":"attacks-against-abstractive-text","title":"Attacks against Abstractive Text Summarization Models through Lead Bias and Influence Functions","date":"2024-10-26","arxiv_id":"2410.20019","repositories_listed":0,"syntology":null},{"url":null,"slug":"regularized-robustly-reliable-learners-and","title":"Regularized Robustly Reliable Learners and Instance Targeted Attacks","date":"2024-10-14","arxiv_id":"2410.10572","repositories_listed":0,"syntology":null},{"url":null,"slug":"provably-reliable-conformal-prediction-sets","title":"Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning","date":"2024-10-13","arxiv_id":"2410.09878","repositories_listed":0,"syntology":null},{"url":null,"slug":"fragile-giants-understanding-the","title":"Fragile Giants: Understanding the Susceptibility of Models to Subpopulation Attacks","date":"2024-10-11","arxiv_id":"2410.08872","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-taggants-dataset-ownership-verification","title":"Data Taggants: Dataset Ownership Verification via Harmless Targeted Data Poisoning","date":"2024-10-09","arxiv_id":"2410.09101","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-adversarial-risk-of-test-time","title":"On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning","date":"2024-10-07","arxiv_id":"2410.04682","repositories_listed":0,"syntology":null},{"url":null,"slug":"empirical-perturbation-analysis-of-linear","title":"Empirical Perturbation Analysis of Linear System Solvers from a Data Poisoning Perspective","date":"2024-10-01","arxiv_id":"2410.00878","repositories_listed":0,"syntology":null},{"url":null,"slug":"survey-of-security-and-data-attacks-on","title":"Survey of Security and Data Attacks on Machine Unlearning In Financial and E-Commerce","date":"2024-09-29","arxiv_id":"2410.00055","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-poisoning-based-backdoor-attack","title":"Data Poisoning-based Backdoor Attack Framework against Supervised Learning Rules of Spiking Neural Networks","date":"2024-09-24","arxiv_id":"2409.15670","repositories_listed":0,"syntology":null},{"url":null,"slug":"shfl-secure-hierarchical-federated-learning","title":"SHFL: Secure Hierarchical Federated Learning Framework for Edge Networks","date":"2024-09-23","arxiv_id":"2409.15067","repositories_listed":0,"syntology":null},{"url":null,"slug":"utrace-poisoning-forensics-for-private","title":"UTrace: Poisoning Forensics for Private Collaborative Learning","date":"2024-09-23","arxiv_id":"2409.15126","repositories_listed":0,"syntology":null},{"url":null,"slug":"clean-label-attacks-against-slu-systems","title":"Clean Label Attacks against SLU Systems","date":"2024-09-13","arxiv_id":"2409.08985","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-is-the-key-backdoor-attacks-for-in","title":"Context is the Key: Backdoor Attacks for In-Context Learning with Vision Transformers","date":"2024-09-06","arxiv_id":"2409.04142","repositories_listed":0,"syntology":null},{"url":null,"slug":"blockchain-based-federated-recommendation","title":"Blockchain-based Federated Recommendation with Incentive Mechanism","date":"2024-09-03","arxiv_id":"2409.01563","repositories_listed":0,"syntology":null},{"url":null,"slug":"protecting-against-simultaneous-data","title":"Protecting against simultaneous data poisoning attacks","date":"2024-08-23","arxiv_id":"2408.13221","repositories_listed":0,"syntology":null},{"url":null,"slug":"unlearnable-examples-detection-via-iterative","title":"Unlearnable Examples Detection via Iterative Filtering","date":"2024-08-15","arxiv_id":"2408.08143","repositories_listed":0,"syntology":null},{"url":null,"slug":"sonic-fast-and-transferable-data-poisoning-on","title":"Sonic: Fast and Transferable Data Poisoning on Clustering Algorithms","date":"2024-08-14","arxiv_id":"2408.07558","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-02813","title":"Mitigating Malicious Attacks in Federated Learning via Confidence-aware Defense","date":"2024-08-05","arxiv_id":"2408.02813","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-02131","title":"Model Hijacking Attack in Federated Learning","date":"2024-08-04","arxiv_id":"2408.02131","repositories_listed":0,"syntology":null},{"url":null,"slug":"blockchain-for-large-language-model-security","title":"Blockchain for Large Language Model Security and Safety: A Holistic Survey","date":"2024-07-26","arxiv_id":"2407.20181","repositories_listed":0,"syntology":null},{"url":null,"slug":"trading-devil-final-backdoor-attack-via-stock","title":"Trading Devil Final: Backdoor attack via Stock market and Bayesian Optimization","date":"2024-07-21","arxiv_id":"2407.14573","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-poisoning-an-overlooked-threat-to-power","title":"Data Poisoning: An Overlooked Threat to Power Grid Resilience","date":"2024-07-19","arxiv_id":"2407.14684","repositories_listed":0,"syntology":null},{"url":null,"slug":"turning-generative-models-degenerate-the","title":"Turning Generative Models Degenerate: The Power of Data Poisoning Attacks","date":"2024-07-17","arxiv_id":"2407.12281","repositories_listed":0,"syntology":null},{"url":null,"slug":"partner-in-crime-boosting-targeted-poisoning","title":"Partner in Crime: Boosting Targeted Poisoning Attacks against Federated Learning","date":"2024-07-13","arxiv_id":"2407.09958","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancements-in-recommender-systems-a","title":"Advancements in Recommender Systems: A Comprehensive Analysis Based on Data, Algorithms, and Evaluation","date":"2024-07-10","arxiv_id":"2407.18937","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuromimetic-metaplasticity-for-adaptive","title":"Neuromimetic metaplasticity for adaptive continual learning","date":"2024-07-09","arxiv_id":"2407.07133","repositories_listed":0,"syntology":null},{"url":null,"slug":"if-you-don-t-understand-it-don-t-use-it","title":"If You Don't Understand It, Don't Use It: Eliminating Trojans with Filters Between Layers","date":"2024-07-08","arxiv_id":"2407.06411","repositories_listed":0,"syntology":null},{"url":null,"slug":"releasing-malevolence-from-benevolence-the","title":"Releasing Malevolence from Benevolence: The Menace of Benign Data on Machine Unlearning","date":"2024-07-06","arxiv_id":"2407.05112","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-robustness-of-graph-reduction-against","title":"On the Robustness of Graph Reduction Against GNN Backdoor","date":"2024-07-02","arxiv_id":"2407.02431","repositories_listed":0,"syntology":null},{"url":null,"slug":"badsampler-harnessing-the-power-of","title":"BadSampler: Harnessing the Power of Catastrophic Forgetting to Poison Byzantine-robust Federated Learning","date":"2024-06-18","arxiv_id":"2406.12222","repositories_listed":0,"syntology":null},{"url":null,"slug":"imperceptible-rhythm-backdoor-attacks","title":"Imperceptible Rhythm Backdoor Attacks: Exploring Rhythm Transformation for Embedding Undetectable Vulnerabilities on Speech Recognition","date":"2024-06-16","arxiv_id":"2406.10932","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-trojans-in-refined-language-models","title":"A Study of Backdoors in Instruction Fine-tuned Language Models","date":"2024-06-12","arxiv_id":"2406.07778","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-vulnerabilities-and-protections-in","title":"Exploring Vulnerabilities and Protections in Large Language Models: A Survey","date":"2024-06-01","arxiv_id":"2406.00240","repositories_listed":0,"syntology":null},{"url":null,"slug":"class-machine-unlearning-for-complex-data-via","title":"Class Machine Unlearning for Complex Data via Concepts Inference and Data Poisoning","date":"2024-05-24","arxiv_id":"2405.15662","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-ai-and-large-language-models-for","title":"Generative AI in Cybersecurity: A Comprehensive Review of LLM Applications and Vulnerabilities","date":"2024-05-21","arxiv_id":"2405.12750","repositories_listed":0,"syntology":null},{"url":null,"slug":"fed-credit-robust-federated-learning-with","title":"Fed-Credit: Robust Federated Learning with Credibility Management","date":"2024-05-20","arxiv_id":"2405.11758","repositories_listed":0,"syntology":null},{"url":null,"slug":"seep-training-dynamics-grounds-latent","title":"SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks","date":"2024-05-19","arxiv_id":"2405.11575","repositories_listed":0,"syntology":null},{"url":null,"slug":"concealing-backdoor-model-updates-in","title":"Concealing Backdoor Model Updates in Federated Learning by Trigger-Optimized Data Poisoning","date":"2024-05-10","arxiv_id":"2405.06206","repositories_listed":0,"syntology":null},{"url":null,"slug":"hard-work-does-not-always-pay-off-poisoning","title":"Hard Work Does Not Always Pay Off: Poisoning Attacks on Neural Architecture Search","date":"2024-05-09","arxiv_id":"2405.06073","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-relevance-of-byzantine-robust","title":"On the Relevance of Byzantine Robust Optimization Against Data Poisoning","date":"2024-05-01","arxiv_id":"2405.00491","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-model-replacement-invisible-multi-target","title":"Dual Model Replacement:invisible Multi-target Backdoor Attack based on Federal Learning","date":"2024-04-22","arxiv_id":"2404.13946","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-poisoning-attacks-on-off-policy-policy","title":"Data Poisoning Attacks on Off-Policy Policy Evaluation Methods","date":"2024-04-06","arxiv_id":"2404.04714","repositories_listed":0,"syntology":null},{"url":null,"slug":"precision-guided-approach-to-mitigate-data","title":"Precision Guided Approach to Mitigate Data Poisoning Attacks in Federated Learning","date":"2024-04-05","arxiv_id":"2404.04139","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-backdoor-approach-with-inverted-labels","title":"A Backdoor Approach with Inverted Labels Using Dirty Label-Flipping Attacks","date":"2024-03-29","arxiv_id":"2404.00076","repositories_listed":0,"syntology":null},{"url":null,"slug":"have-you-poisoned-my-data-defending-neural","title":"Have You Poisoned My Data? Defending Neural Networks against Data Poisoning","date":"2024-03-20","arxiv_id":"2403.13523","repositories_listed":0,"syntology":null},{"url":null,"slug":"don-t-forget-what-i-did-assessing-client","title":"Don't Forget What I did?: Assessing Client Contributions in Federated Learning","date":"2024-03-11","arxiv_id":"2403.07151","repositories_listed":0,"syntology":null},{"url":null,"slug":"poisoning-programs-by-un-repairing-code","title":"Poisoning Programs by Un-Repairing Code: Security Concerns of AI-generated Code","date":"2024-03-11","arxiv_id":"2403.06675","repositories_listed":0,"syntology":null},{"url":null,"slug":"breaking-down-the-defenses-a-comparative","title":"Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Models","date":"2024-03-03","arxiv_id":"2403.04786","repositories_listed":0,"syntology":null},{"url":null,"slug":"indiscriminate-data-poisoning-attacks-on-pre","title":"Indiscriminate Data Poisoning Attacks on Pre-trained Feature Extractors","date":"2024-02-20","arxiv_id":"2402.12626","repositories_listed":0,"syntology":null},{"url":null,"slug":"purifying-large-language-models-by-ensembling","title":"Purifying Large Language Models by Ensembling a Small Language Model","date":"2024-02-19","arxiv_id":"2402.14845","repositories_listed":0,"syntology":null},{"url":null,"slug":"susfl-energy-aware-federated-learning-based","title":"SusFL: Energy-Aware Federated Learning-based Monitoring for Sustainable Smart Farms","date":"2024-02-15","arxiv_id":"2402.10280","repositories_listed":0,"syntology":null},{"url":null,"slug":"review-incorporated-model-agnostic-profile","title":"Review-Incorporated Model-Agnostic Profile Injection Attacks on Recommender Systems","date":"2024-02-14","arxiv_id":"2402.09023","repositories_listed":0,"syntology":null},{"url":null,"slug":"security-and-privacy-challenges-of-large","title":"Security and Privacy Challenges of Large Language Models: A Survey","date":"2024-01-30","arxiv_id":"2402.00888","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-learning-with-dual-attention-for","title":"Federated Learning with Dual Attention for Robust Modulation Classification under Attacks","date":"2024-01-19","arxiv_id":"2401.11039","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-gan-based-data-poisoning-framework-against","title":"A GAN-based data poisoning framework against anomaly detection in vertical federated learning","date":"2024-01-17","arxiv_id":"2401.08984","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-stronger-the-diffusion-model-the-easier","title":"The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright Breaches Without Adjusting Finetuning Pipeline","date":"2024-01-07","arxiv_id":"2401.04136","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-dependent-stability-analysis-of","title":"Data-Dependent Stability Analysis of Adversarial Training","date":"2024-01-06","arxiv_id":"2401.03156","repositories_listed":0,"syntology":null},{"url":null,"slug":"revamping-federated-learning-security-from-a","title":"Revamping Federated Learning Security from a Defender's Perspective: A Unified Defense with Homomorphic Encrypted Data Space","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ssl-ota-unveiling-backdoor-threats-in-self","title":"SSL-OTA: Unveiling Backdoor Threats in Self-Supervised Learning for Object Detection","date":"2023-12-30","arxiv_id":"2401.00137","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-data-poisoning-for-fake-news","title":"Adversarial Data Poisoning for Fake News Detection: How to Make a Model Misclassify a Target News without Modifying It","date":"2023-12-23","arxiv_id":"2312.15228","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-machines-learn-robustly-privately-and","title":"Balancing Privacy, Robustness, and Efficiency in Machine Learning","date":"2023-12-22","arxiv_id":"2312.14712","repositories_listed":0,"syntology":null},{"url":null,"slug":"trojfsp-trojan-insertion-in-few-shot-prompt","title":"TrojFSP: Trojan Insertion in Few-shot Prompt Tuning","date":"2023-12-16","arxiv_id":"2312.10467","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-and-model-poisoning-backdoor-attacks-on","title":"Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Survey","date":"2023-12-14","arxiv_id":"2312.08667","repositories_listed":0,"syntology":null},{"url":null,"slug":"forcing-generative-models-to-degenerate-ones","title":"Forcing Generative Models to Degenerate Ones: The Power of Data Poisoning Attacks","date":"2023-12-07","arxiv_id":"2312.04748","repositories_listed":0,"syntology":null},{"url":null,"slug":"fedbayes-a-zero-trust-federated-learning","title":"FedBayes: A Zero-Trust Federated Learning Aggregation to Defend Against Adversarial Attacks","date":"2023-12-04","arxiv_id":"2312.04587","repositories_listed":0,"syntology":null},{"url":null,"slug":"mendata-a-framework-to-purify-manipulated","title":"Mendata: A Framework to Purify Manipulated Training Data","date":"2023-12-03","arxiv_id":"2312.01281","repositories_listed":0,"syntology":null}],"record_sha256":"442d218312cca7ba5c2ac0ea3eaefb55c67774c113f943ab149c5da8cdb3390a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}